{"object":"list","data":[{"api":"chat","id":"zai/glm-5.1","object":"model","created":1775577600,"owned_by":"system","input_price":0.0000014,"cached_price":2.6e-7,"output_price":0.0000044,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Compared with GLM-5, GLM-5.1 delivers significant improvements in coding, agentic tool usage, reasoning, role-play, and general chat quality. Besides, GLM-5.1 has outstanding capabilities in long-horizon agentic tasks like CUDA kernel optimization.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"zai/glm-5.2","object":"model","created":1781619097,"owned_by":"system","input_price":0.0000014,"cached_price":2.6e-7,"output_price":0.0000044,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5.2 is the latest model in Z.ai's GLM series, continuing the line's focus on coding and long-horizon agentic tasks. Like GLM-5.1, it is designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"zai/GLM-4.5","object":"model","created":1760609788,"owned_by":"system","input_price":6e-7,"cached_price":1.1e-7,"output_price":0.0000022,"max_output_tokens":98304,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-4.5 and GLM-4.5-Air are Z AI's latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"zai/GLM-4.6","object":"model","created":1760609788,"owned_by":"system","input_price":6e-7,"cached_price":1.1e-7,"output_price":0.0000022,"max_output_tokens":128000,"context_window":200000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-4.6 is Z AI’s latest flagship model, designed to push agentic and coding performance further. It expands the context window from 128K to 200K tokens, improves reasoning and tool-use capabilities, and delivers stronger results in coding benchmarks and real-world development workflows. GLM-4.6 demonstrates refined writing quality, more capable agent behavior, and higher token efficiency (≈15% fewer tokens vs. GLM-4.5).\n\nEvaluations show clear gains over GLM-4.5 across reasoning, agents, and coding, reaching near parity with Claude Sonnet 4 in practical tasks while outperforming other open-source baselines. GLM-4.6 is available through the Z.ai API platform, OpenRouter, coding agents (Claude Code, Roo Code, Cline, Kilo Code), and soon as downloadable weights on HuggingFace and ModelScope.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"zai/GLM-5","object":"model","created":1770825600,"owned_by":"system","input_price":0.000001,"cached_price":2e-7,"output_price":0.0000032,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5 is Zai’s new-generation flagship foundation model, designed for Agentic Engineering, capable of providing reliable productivity in complex system engineering and long-range Agent tasks. In terms of Coding and Agent capabilities, GLM-5 has achieved state-of-the-art (SOTA) performance in open source, with its usability in real programming scenarios approaching that of Claude Opus 4.5.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"zai/GLM-4.7","object":"model","created":1765880188,"owned_by":"system","input_price":6e-7,"cached_price":1.1e-7,"output_price":0.0000022,"max_output_tokens":128000,"context_window":200000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-4.7 is Z AI’s latest flagship model, designed to push agentic and coding performance further. It expands the context window from 128K to 200K tokens, improves reasoning and tool-use capabilities, and delivers stronger results in coding benchmarks and real-world development workflows. GLM-4.6 demonstrates refined writing quality, more capable agent behavior, and higher token efficiency (≈15% fewer tokens vs. GLM-4.5).\n\nEvaluations show clear gains over GLM-4.5 across reasoning, agents, and coding, reaching near parity with Claude Sonnet 4 in practical tasks while outperforming other open-source baselines. GLM-4.6 is available through the Z.ai API platform, OpenRouter, coding agents (Claude Code, Roo Code, Cline, Kilo Code), and soon as downloadable weights on HuggingFace and ModelScope.","privacy_comments":"N/A","geolocation":"sg"},{"api":"chat","id":"anthropic/claude-opus-4-8","object":"model","created":1779987112,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.8 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.7, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-opus-4-1","object":"model","created":1754414845,"owned_by":"system","input_price":0.000015,"caching_price":0.00001875,"cached_price":0.0000015,"output_price":0.000075,"max_output_tokens":32000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4 is Anthropic's most powerful model yet and the best coding model in the world, leading on SWE-bench (72.5%) and Terminal-bench (43.2%). It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, with the ability to work continuously for several hours—dramatically outperforming all Sonnet models and significantly expanding what AI agents can accomplish.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-fable-5","object":"model","created":1781028000,"owned_by":"system","input_price":0.00001,"caching_price":0.0000125,"cached_price":0.000001,"output_price":0.00005,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-sonnet-5","object":"model","created":1782838924,"owned_by":"system","input_price":0.000002,"caching_price":0.0000025,"cached_price":2e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 5 is the latest model in the Sonnet family and an upgrade to Sonnet 4.6, with gains in agentic coding and professional work. It delivers top-tier intelligence at Sonnet pricing, well suited to production agents, high-volume pipelines, and everyday professional work like document drafting, spreadsheet analysis, and presentations.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-opus-4-5","object":"model","created":1754414845,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-haiku-4-5","object":"model","created":1764004371,"owned_by":"system","input_price":0.000001,"caching_price":0.00000125,"cached_price":1e-7,"output_price":0.000005,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-opus-4-7","object":"model","created":1776356268,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-opus-4-6","object":"model","created":1770314250,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.6 is Anthropic's most powerful model yet and the best coding model in the world.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-sonnet-4-6","object":"model","created":1771351251,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"anthropic/claude-sonnet-4-5","object":"model","created":1759165971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.5 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen-max","object":"model","created":1745882204,"owned_by":"system","input_price":0.0000016,"caching_price":0.0000016,"cached_price":0.0000016,"output_price":0.0000064,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3-30b-a3b-instruct-2507","object":"model","created":1753953463,"owned_by":"system","input_price":2e-7,"caching_price":8e-7,"cached_price":2e-7,"output_price":8e-7,"max_output_tokens":65536,"context_window":131072,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen-plus","object":"model","created":1745882204,"owned_by":"system","input_price":4e-7,"caching_price":4e-7,"cached_price":4e-7,"output_price":0.0000012,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3-coder-flash","object":"model","created":1753348663,"owned_by":"system","input_price":3e-7,"caching_price":3e-7,"cached_price":8e-8,"output_price":0.0000015,"max_output_tokens":65536,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3 Coder Flash","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3.7-plus","object":"model","created":1781341127,"owned_by":"system","input_price":3.2e-7,"caching_price":4e-7,"cached_price":3.2e-8,"output_price":0.00000128,"max_output_tokens":65536,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3-coder-plus","object":"model","created":1753348663,"owned_by":"system","input_price":0.000001,"output_price":0.000005,"max_output_tokens":65536,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3 Coder Plus","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3.7-max","object":"model","created":1779791470,"owned_by":"system","input_price":0.0000025,"caching_price":0.000003125,"cached_price":2.5e-7,"output_price":0.0000075,"max_output_tokens":65536,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3.6-plus","object":"model","created":1779871716,"owned_by":"system","input_price":5e-7,"caching_price":6.25e-7,"cached_price":5e-8,"output_price":0.000003,"max_output_tokens":65536,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.6-Plus is Alibaba's flagship with hybrid attention and sparse MoE architecture. Features 1M-token native context with always-on reasoning and near-frontier performance on coding and agentic benchmarks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen3-max","object":"model","created":1757524929,"owned_by":"system","input_price":8.61e-7,"output_price":0.000003441,"max_output_tokens":65536,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"This is the best-performing model in the Qwen series. It is ideal for complex, multi-step tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"alibaba/qwen-turbo","object":"model","created":1745882204,"owned_by":"system","input_price":5e-8,"caching_price":5e-8,"cached_price":5e-8,"output_price":2e-7,"max_output_tokens":0,"context_window":1000000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/kimi-k2.7-code","object":"model","created":1781341290,"owned_by":"system","input_price":9.5e-7,"cached_price":1.9e-7,"output_price":0.000004,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/qwen3.7-plus","object":"model","created":1781351147,"owned_by":"system","input_price":4e-7,"cached_price":8e-8,"output_price":0.0000016,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/minimax-m2.5","object":"model","created":1775122792,"owned_by":"system","input_price":3e-7,"cached_price":3e-8,"output_price":0.0000012,"max_output_tokens":24576,"context_window":196608,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"MiniMax M2.5 is built for state-of-the-art coding, agentic tool use, search, and office work, extensively trained with reinforcement learning across hundreds of thousands of real-world environments to plan like an architect and generalize across unfamiliar scaffolding and tools. It delivers significantly faster task completion, improved token efficiency, and exceptional cost-effectiveness, making it well-suited for production-scale agentic applications and complex, multi-step workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/deepseek-v4-pro","object":"model","created":1777470408,"owned_by":"system","input_price":0.00000174,"cached_price":1.5e-7,"output_price":0.00000348,"max_output_tokens":131072,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4 Pro is a flagship open source Mixture of Experts model designed for frontier reasoning, advanced coding, and long context intelligence at scale (up to 1M tokens). It introduces a hybrid attention architecture that dramatically improves long context efficiency while reducing KV and compute overhead, along with stability and training enhancements for deep multi step reasoning. It represents a top tier open source system for complex agentic workflows, high precision reasoning, and demanding production workloads.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/minimax-m3","object":"model","created":1781341681,"owned_by":"system","input_price":3e-7,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":512000,"context_window":512000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"MiniMax-M3 is a native multimodal model with 512K context running ~428B parameters and ~23B activated parameters. It brings native multimodality, enabling deeper semantic fusion across text, image, and video. M3 also introduces MiniMax Sparse Attention (MSA) to improve long context efficiency, achieving frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/kimi-k2.5","object":"model","created":1774956928,"owned_by":"system","input_price":6e-7,"cached_price":1e-7,"output_price":0.000003,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/glm-5.2-fast","object":"model","created":1783970937,"owned_by":"system","input_price":0.0000021,"cached_price":2.1e-7,"output_price":0.0000066,"max_output_tokens":131072,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-horizon tasks. Its new IndexShare architecture and improved MTP layer simultaneously boost efficiency by reducing per-token FLOPs and increasing speculative decoding lengths. A 743B-parameter model in Zhipu AI's GLM series, designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/glm-5.2","object":"model","created":1781645882,"owned_by":"system","input_price":0.0000014,"cached_price":1.4e-7,"output_price":0.0000044,"max_output_tokens":131072,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-horizon tasks. Its new IndexShare architecture and improved MTP layer simultaneously boost efficiency by reducing per-token FLOPs and increasing speculative decoding lengths. A 743B-parameter model in Zhipu AI's GLM series, designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/minimax-m2.7","object":"model","created":1777470703,"owned_by":"system","input_price":3e-7,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":24576,"context_window":196608,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Mixture of Experts language model. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/qwen3.6-plus","object":"model","created":1777476184,"owned_by":"system","input_price":5e-7,"cached_price":1e-7,"output_price":0.000003,"max_output_tokens":4000,"context_window":131072,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen 3.6 Plus is Alibaba's latest flagship closed model, available exclusively through Fireworks AI outside of Alibaba's own infrastructure. Please contact Fireworks AI to get dedicated instances for Qwen 3.6 Plus.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/glm-5.1","object":"model","created":1777470462,"owned_by":"system","input_price":0.0000014,"cached_price":2.6e-7,"output_price":0.0000044,"max_output_tokens":25344,"context_window":202000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM 5.1 is Z.ai's next generation flagship model built for agentic engineering, with stronger coding capabilities and sustained performance over long horizon tasks with hundreds of iteration rounds. It's a 754B parameter MoE model.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/deepseek-v4-flash","object":"model","created":1779870790,"owned_by":"system","input_price":1.4e-7,"cached_price":3e-8,"output_price":2.8e-7,"max_output_tokens":131072,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4 Flash is a streamlined open-source Mixture-of-Experts model (284B parameters) optimized for fast, cost-efficient inference while preserving strong reasoning and coding performance at 1M token context scale. It leverages hybrid attention innovations for lower latency and higher throughput, delivering near-Pro reasoning quality ideal for interactive agents and high-volume production workloads.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/kimi-k2.6","object":"model","created":1777027118,"owned_by":"system","input_price":9.5e-7,"cached_price":1.6e-7,"output_price":0.000004,"max_output_tokens":32768,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration. It features a 1028B Mixture-of-Experts architecture and supports vision, function calling, and agentic paradigms.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/nemotron-3-ultra-nvfp4","object":"model","created":1781342122,"owned_by":"system","input_price":6e-7,"cached_price":1.2e-7,"output_price":0.0000024,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/gpt-oss-20b","object":"model","created":1779870794,"owned_by":"system","input_price":7e-8,"cached_price":3.5e-8,"output_price":3e-7,"max_output_tokens":65536,"context_window":131072,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GPT-OSS-20B is OpenAI's lightweight open-weight model with 21.5 billion total parameters (3.6 billion active, Mixture-of-Experts). Optimized for lower latency and local or specialized use cases including agentic tasks, chain-of-thought reasoning, and web browsing. Released under Apache 2.0 license.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"fireworks/gpt-oss-120b","object":"model","created":1779870796,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-8,"output_price":6e-7,"max_output_tokens":65536,"context_window":131072,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GPT-OSS-120B is OpenAI's open-weight large language model with 116 billion total parameters (5.1 billion active, Mixture-of-Experts). Designed for high-performance reasoning, agentic tasks, function calling, and general-purpose applications. Supports configurable reasoning depth and chain-of-thought. Released under Apache 2.0 license.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"inceptron/glm-5.2","object":"model","created":1782554144,"owned_by":"system","input_price":0.0000012,"cached_price":2.6e-7,"output_price":0.0000042,"max_output_tokens":1000000,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GLM 5.2 is the latest Z.ai flagship model for long horizon coding, reasoning, and agentic workflows. It improves on GLM 5.1 with a 1M token context window, stronger engineering task performance, multiple thinking effort levels, and architectural changes that reduce long context inference cost while improving speculative decoding. Released under the MIT license, it is designed for sustained work over large repositories, complex tool use, and multi step technical tasks.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"inceptron/minimax-m2.5","object":"model","created":1777477859,"owned_by":"system","input_price":2.8e-7,"cached_price":3e-8,"output_price":0.0000011,"max_output_tokens":196608,"context_window":196608,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is a state of the art language model built for real world productivity and autonomous agent execution. Trained with large scale reinforcement learning across hundreds of thousands of complex digital environments, it delivers leading performance in coding, search, tool use, and professional office workflows, operating with significantly improved speed and token efficiency. Designed to plan like an architect and act with cost efficient precision, M2.5 extends beyond software development into finance, research, and enterprise grade office tasks, bringing high end agentic capability at a fraction of the typical frontier model cost.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"inceptron/kimi-k2.7-Code","object":"model","created":1782218309,"owned_by":"system","input_price":7.5e-7,"cached_price":2e-7,"output_price":0.0000035,"max_output_tokens":256000,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Kimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, tuned for long-horizon software engineering workflows, multi-step tool use, and end-to-end task completion. It keeps the trillion-parameter MoE architecture with roughly 32B active parameters, a 256K-token context window, native INT4 quantization, and multimodal image and video input support while reducing thinking-token usage compared with K2.6.","privacy_comments":"No training on user data.","geolocation":"eu"},{"api":"chat","id":"inceptron/kimi-k2.6","object":"model","created":1777476469,"owned_by":"system","input_price":8e-7,"cached_price":2e-7,"output_price":0.0000035,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.6 is Moonshot AI's latest open weight reasoning model, built for long horizon coding, agentic execution, and multimodal reasoning. It retains the trillion parameter MoE architecture with roughly 32B active parameters and a 256k token context window, while improving agentic benchmark performance and knowledge reliability over K2.5. Native text, image, and video input plus tool driven workflows make it well suited for coding, research, and complex multi step tasks.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"sference/thinkingcap-qwen3.6-27b","object":"model","created":1783965561,"owned_by":"system","input_price":4e-7,"cached_price":2.6e-7,"output_price":0.000003,"max_output_tokens":32768,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"ThinkingCap-Qwen3.6-27B is a reasoning tuned model from BottlecapAI built on Qwen3.6 27B. It supports extended thinking with tool calling and a 256K context window. Served via Sference.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"sference/qwen3guard-gen-8b","object":"model","created":1783350339,"owned_by":"system","input_price":5e-8,"cached_price":0,"output_price":4e-7,"max_output_tokens":8192,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen3Guard-Gen-8B is an 8 billion parameter multilingual safety moderation model from Alibaba. Built as a guardrail, it evaluates full user prompts and model responses across 119 languages and classifies content severity into three tiers: Safe, Controversial, and Unsafe. Served via Sference.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"sference/glm-5.2","object":"model","created":1783350238,"owned_by":"system","input_price":0.0000012,"cached_price":2.6e-7,"output_price":0.0000042,"max_output_tokens":131072,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GLM-5.2 is the latest model in the GLM series from Z.ai, continuing its focus on coding and long horizon agentic work. Building on GLM-5.1, it plans, executes, and iterates autonomously on extended engineering grade tasks. Served via Sference.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"parasail/parasail-deepseek-v4-flash","object":"model","created":1781381768,"owned_by":"system","input_price":1.4e-7,"cached_price":7e-8,"output_price":2.8e-7,"max_output_tokens":8192,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek-V4-Flash","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/parasail-qwen25-vl-72b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":7e-7,"cached_price":7e-7,"output_price":7e-7,"max_output_tokens":8192,"context_window":32768,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen 2.5 VL 72B Instruct","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/parasail-qwen3-235b-a22b-instruct-2507","object":"model","created":1753115020,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":8.5e-7,"max_output_tokens":8192,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen 3 235B a22b Instruct","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/Kimi K2.5","object":"model","created":1774953955,"owned_by":"system","input_price":6e-7,"output_price":0.0000028,"max_output_tokens":131072,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/google/gemma-4-26B-A4B-it","object":"model","created":1779719796,"owned_by":"system","input_price":1.3e-7,"cached_price":5e-8,"output_price":4e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemma 4 26B A4B is a Mixture of Experts model from Google DeepMind built for scalable performance with a 256K context window. Supports text and image input, native thinking mode, function calling, and 140+ languages. Ideal for long context RAG, agentic workflows, coding, and multimodal understanding.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/parasail-gemma3-27b-it","object":"model","created":1741963556,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":5e-7,"max_output_tokens":8192,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemma 3 1B is the smallest of the new Gemma 3 family. It handles context windows up to 32k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Note: Gemma 3 1B is not multimodal. For the smallest multimodal Gemma 3 model, please see [Gemma 3 4B](google/gemma-3-4b-it)","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"parasail/kimi-k2.7-code","object":"model","created":1781381767,"owned_by":"system","input_price":7.5e-7,"cached_price":1.6e-7,"output_price":0.0000035,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 262K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/glm-5.2:flex","object":"model","created":1782230293,"owned_by":"system","input_price":0.00000105,"output_price":0.0000033,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Z.ai's next-generation flagship model for agentic software engineering, with significantly stronger coding capabilities than GLM-5.1.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/nvidia-nemotron-3-ultra:flex","object":"model","created":1782230296,"owned_by":"system","input_price":3.7e-7,"output_price":0.00000187,"max_output_tokens":131072,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Ultra is NVIDIA's strongest open-weights reasoning model, positioned near GPT-5.4 Mini (xhigh) and ahead of DeepSeek V4-Flash and Qwen3.5-397B-A17B.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/deepseek-v4-pro","object":"model","created":1782230297,"owned_by":"system","input_price":0.00000174,"output_price":0.00000348,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4-Pro is DeepSeek's flagship open-weights MoE model, with performance in the same class as Claude Sonnet 4.6 and stronger overall results than GLM-5.1.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/deepseek-v4-pro:flex","object":"model","created":1782230299,"owned_by":"system","input_price":0.00000131,"output_price":0.00000275,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4-Pro is DeepSeek's flagship open-weights MoE model, with performance in the same class as Claude Sonnet 4.6 and stronger overall results than GLM-5.1.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/deepseek-v4-flash","object":"model","created":1782230301,"owned_by":"system","input_price":1.4e-7,"output_price":2.8e-7,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4-Flash is the smaller model in the V4 family, ahead of models like Gemini 3 Flash and Qwen3.5-397B-A17B.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/deepseek-v4-flash:flex","object":"model","created":1782230303,"owned_by":"system","input_price":1e-7,"output_price":2e-7,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek V4-Flash is the smaller model in the V4 family, ahead of models like Gemini 3 Flash and Qwen3.5-397B-A17B.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/glm-5.2","object":"model","created":1782230288,"owned_by":"system","input_price":0.0000014,"output_price":0.0000044,"max_output_tokens":131072,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Z.ai's next-generation flagship model for agentic software engineering, with significantly stronger coding capabilities than GLM-5.1.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"doubleword/nvidia-nemotron-3-ultra","object":"model","created":1782230290,"owned_by":"system","input_price":5e-7,"output_price":0.0000025,"max_output_tokens":131072,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Ultra is NVIDIA's strongest open-weights reasoning model, positioned near GPT-5.4 Mini (xhigh) and ahead of DeepSeek V4-Flash and Qwen3.5-397B-A17B.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"sakana/fugu-ultra","object":"model","created":1782132799,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":131072,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Fugu Ultra is built on a pool of publicly accessible frontier models, rather than running as a single model. It coordinates several models, routing work to 1-3 agents depending on the problem and combining their results into a single answer.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"moonshot/kimi-k2.7-code","object":"model","created":1781360299,"owned_by":"system","input_price":9.5e-7,"cached_price":1.9e-7,"output_price":0.000004,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"moonshot/kimi-k2.6","object":"model","created":1776704451,"owned_by":"system","input_price":9.5e-7,"cached_price":1.6e-7,"output_price":0.000004,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"moonshot/kimi-k2.5","object":"model","created":1770289011,"owned_by":"system","input_price":6e-7,"cached_price":1e-7,"output_price":0.000003,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"poolside/laguna-m.1","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Poolside Laguna M.1 — a mid-size code-focused LLM from Poolside, served via an OpenAI-compatible API.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"Governed by Poolside terms of service.","geolocation":"global"},{"api":"chat","id":"poolside/laguna-xs.2","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Poolside Laguna XS.2 — a small, fast code-focused LLM from Poolside, served via an OpenAI-compatible API.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"Governed by Poolside terms of service.","geolocation":"global"},{"api":"chat","id":"xai/grok-3-mini","object":"model","created":1760609788,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":5e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-3-mini:low","object":"model","created":1760609788,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":5e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4","object":"model","created":1760609788,"owned_by":"system","input_price":0.000003,"caching_price":0.000003,"cached_price":7.5e-7,"output_price":0.000015,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"xAI's latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4-fast-non-reasoning","object":"model","created":1760609788,"owned_by":"system","input_price":2e-7,"caching_price":2e-7,"cached_price":5e-8,"output_price":5e-7,"max_output_tokens":0,"context_window":2000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"xAI's latest advancement in cost-efficient reasoning models","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-3-mini:high","object":"model","created":1760609788,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":5e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4-1-fast-non-reasoning","object":"model","created":1764609284,"owned_by":"system","input_price":2e-7,"caching_price":2e-7,"cached_price":5e-8,"output_price":5e-7,"max_output_tokens":0,"context_window":2000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A frontier multimodal model optimized specifically for high-performance agentic tool calling.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4.2-beta","object":"model","created":1773944308,"owned_by":"system","input_price":0.000002,"caching_price":0.000002,"cached_price":2e-7,"output_price":0.000006,"max_output_tokens":0,"context_window":2000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4.5","object":"model","created":1783534655,"owned_by":"system","input_price":0.000002,"caching_price":0.000002,"cached_price":5e-7,"output_price":0.000006,"max_output_tokens":0,"context_window":500000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Grok 4.5 is xAI's frontier multimodal model for advanced coding, knowledge work, STEM reasoning, and agentic workflows. It supports text and image inputs with text output, tool calling, structured outputs, web search, and extended reasoning. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-build-0.1","object":"model","created":1779871707,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000002,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Grok Build 0.1 is xAI's dedicated coding model optimized for software engineering tasks including code generation, review, debugging, and technical problem solving.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-code-fast-1","object":"model","created":1760609788,"owned_by":"system","input_price":2e-7,"cached_price":2e-8,"output_price":0.0000015,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A speedy and economical reasoning model that excels at agentic coding","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4.3","object":"model","created":1777635042,"owned_by":"system","input_price":0.00000125,"caching_price":0.00000125,"cached_price":2e-7,"output_price":0.0000025,"max_output_tokens":0,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning is always active and cannot be disabled or configured by effort level. It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4-1-fast-reasoning","object":"model","created":1764609284,"owned_by":"system","input_price":2e-7,"caching_price":2e-7,"cached_price":5e-8,"output_price":5e-7,"max_output_tokens":0,"context_window":2000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A frontier multimodal model optimized specifically for high-performance agentic tool calling.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-3","object":"model","created":1760609788,"owned_by":"system","input_price":0.000005,"cached_price":0.000005,"output_price":0.000025,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xai/grok-4-fast","object":"model","created":1760609788,"owned_by":"system","input_price":2e-7,"caching_price":2e-7,"cached_price":5e-8,"output_price":5e-7,"max_output_tokens":0,"context_window":2000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"xAI's latest advancement in cost-efficient reasoning models","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3-pro-image-preview","object":"model","created":1746582113,"owned_by":"system","input_price":0.000002,"caching_price":0.0000045,"cached_price":2e-7,"output_price":0.000012,"max_output_tokens":32768,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 3 Pro Image, or Gemini 3 Pro (with Nano Banana), is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It's the best model for complex and multi-turn image generation and editing, having improved accuracy and enhanced image quality.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-central1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/claude-sonnet-5","object":"model","created":1782839345,"owned_by":"system","input_price":0.000002,"caching_price":0.0000025,"cached_price":2e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 5 is the latest model in the Sonnet family and an upgrade to Sonnet 4.6, with gains in agentic coding and professional work. It delivers top-tier intelligence at Sonnet pricing, well suited to production agents, high-volume pipelines, and everyday professional work like document drafting, spreadsheet analysis, and presentations.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000015,"caching_price":0.00001875,"cached_price":0.0000015,"output_price":0.000075,"max_output_tokens":32000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-central2","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-3.1-pro-preview:flex","object":"model","created":1771524000,"owned_by":"system","input_price":0.000001,"caching_price":0.00000275,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Pro is the next iteration in the Gemini 3 series of models, a suite of highly capable, natively multimodal reasoning models. As of this model card’s date of publication, Gemini 3.1 Pro is Google’s most advanced model for complex tasks. Geminin 3.1 Pro can comprehend vast datasets and challenging problems from massively multimodal information sources, including text, audio, images, video, and entire code repositories.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash@us-south1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@us-east1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@europe-central2","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3.5-flash@eu","object":"model","created":1779225804,"owned_by":"system","input_price":0.0000015,"caching_price":0.000001583,"cached_price":1.5e-7,"output_price":0.000009,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-west4","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/claude-opus-4-5@us-east5","object":"model","created":1764004371,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-southwest1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash@europe-central2","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@europe-west8","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-west1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-3-flash-preview:flex","object":"model","created":1766022113,"owned_by":"system","input_price":2.5e-7,"caching_price":5e-7,"cached_price":2.5e-8,"output_price":0.0000015,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3 Flash Preview is designed to deliver strong agentic capabilities (near-Pro level) at substantial speed and value. Making it perfect for engaging multi-turn chats, and collaborating back and forth with your coding agent without getting out of flow. Compared to 2.5 Flash it delivers significant improvements across the board.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-east4","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash@us-east5","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4-5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-1@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000015,"caching_price":0.00001875,"cached_price":0.0000015,"output_price":0.000075,"max_output_tokens":32000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-haiku-4-5@europe-west1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/claude-sonnet-4-6@europe-west1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/claude-opus-4-8@us","object":"model","created":1779987115,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.8 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.7, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.8 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/claude-opus-4","object":"model","created":1747933971,"owned_by":"system","input_price":0.000015,"caching_price":0.00001875,"cached_price":0.0000015,"output_price":0.000075,"max_output_tokens":32000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@us-central1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-7@us","object":"model","created":1770317868,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-2.5-flash@us-west1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4-6@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@us-south1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash@us-east1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-7@eu","object":"model","created":1770317868,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash@europe-north1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@us-east5","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-west8","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/claude-opus-4-6@us-east5","object":"model","created":1770317868,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.6 is Anthropic's most powerful model yet and the best coding model in the world.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-3.1-pro-preview","object":"model","created":1771524000,"owned_by":"system","input_price":0.000002,"caching_price":0.0000045,"cached_price":2e-7,"output_price":0.000012,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Pro is the next iteration in the Gemini 3 series of models, a suite of highly capable, natively multimodal reasoning models. As of this model card’s date of publication, Gemini 3.1 Pro is Google’s most advanced model for complex tasks. Geminin 3.1 Pro can comprehend vast datasets and challenging problems from massively multimodal information sources, including text, audio, images, video, and entire code repositories.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@europe-west1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-fable-5","object":"model","created":1781015529,"owned_by":"system","input_price":0.00001,"caching_price":0.0000125,"cached_price":0.000001,"output_price":0.00005,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4-5@europe-west1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.00000413,"cached_price":3.3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash@europe-west4","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3.1-flash-image-preview","object":"model","created":1772125200,"owned_by":"system","input_price":5e-7,"caching_price":0,"cached_price":0,"output_price":0.000002,"max_output_tokens":32768,"context_window":131072,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 3.1 Flash Image is optimized for image understanding and generation and offers a balance of price and performance.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3-pro-preview","object":"model","created":1771524000,"owned_by":"system","input_price":0.000002,"caching_price":0.0000045,"cached_price":2e-7,"output_price":0.000012,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Pro is the next iteration in the Gemini 3 series of models, a suite of highly capable, natively multimodal reasoning models. As of this model card’s date of publication, Gemini 3.1 Pro is Google’s most advanced model for complex tasks. Geminin 3.1 Pro can comprehend vast datasets and challenging problems from massively multimodal information sources, including text, audio, images, video, and entire code repositories.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-8@eu","object":"model","created":1779987117,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.8 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.7, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.8 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/claude-opus-4-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000015,"caching_price":0.00001875,"cached_price":0.0000015,"output_price":0.000075,"max_output_tokens":32000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@europe-west4","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-5@us","object":"model","created":1782839346,"owned_by":"system","input_price":0.0000022,"caching_price":0.00000275,"cached_price":2.2e-7,"output_price":0.000011,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 5 is the latest model in the Sonnet family and an upgrade to Sonnet 4.6, with gains in agentic coding and professional work. It delivers top-tier intelligence at Sonnet pricing, well suited to production agents, high-volume pipelines, and everyday professional work like document drafting, spreadsheet analysis, and presentations.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-3.5-flash","object":"model","created":1779225804,"owned_by":"system","input_price":0.0000015,"caching_price":0.000001583,"cached_price":1.5e-7,"output_price":0.000009,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-8","object":"model","created":1779987109,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.8 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.7, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.8 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-west4","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@us-east5","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-haiku-4-5@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-3-flash-preview","object":"model","created":1766022113,"owned_by":"system","input_price":5e-7,"caching_price":0.000001,"cached_price":5e-8,"output_price":0.000003,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3 Flash Preview is designed to deliver strong agentic capabilities (near-Pro level) at substantial speed and value. Making it perfect for engaging multi-turn chats, and collaborating back and forth with your coding agent without getting out of flow. Compared to 2.5 Flash it delivers significant improvements across the board.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/kimi-k2","object":"model","created":1776345053,"owned_by":"system","input_price":6e-7,"caching_price":0.0000025,"cached_price":6e-8,"output_price":0.0000025,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2 Thinking is an open-source model that operates as a \"thinking agent,\" reasoning step-by-step while using tools to achieve state-of-the-art performance on various benchmarks. It is capable of executing up to 200-300 sequential tool calls without human intervention, allowing it to solve complex problems across a wide range of tasks. The model uses Quantization-Aware Training (QAT) to support INT4 inference, which provides a roughly 2x improvement in generation speed.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3.1-flash-lite","object":"model","created":1778175883,"owned_by":"system","input_price":2.5e-7,"caching_price":8.333e-8,"cached_price":2.5e-8,"output_price":0.0000015,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Flash Lite Preview is the most cost-efficient model in the Gemini family, optimized for high-volume, low-latency tasks. It delivers fast responses with solid quality for everyday use cases including summarization, classification, and simple reasoning.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@europe-north1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash@us-central1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash@europe-west1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-5","object":"model","created":1764004371,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4-5@us-east5","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.00000413,"cached_price":3.3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/claude-opus-4-7","object":"model","created":1770317868,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-north1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@europe-west8","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-haiku-4-5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000001,"caching_price":0.00000125,"cached_price":1e-7,"output_price":0.000005,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4-6","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-5@europe-west1","object":"model","created":1764004371,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@europe-central2","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@europe-west1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash@europe-west8","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-5@eu","object":"model","created":1782839348,"owned_by":"system","input_price":0.0000022,"caching_price":0.00000275,"cached_price":2.2e-7,"output_price":0.000011,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 5 is the latest model in the Sonnet family and an upgrade to Sonnet 4.6, with gains in agentic coding and professional work. It delivers top-tier intelligence at Sonnet pricing, well suited to production agents, high-volume pipelines, and everyday professional work like document drafting, spreadsheet analysis, and presentations.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@europe-north1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-opus-4-6@europe-west1","object":"model","created":1770317868,"owned_by":"system","input_price":0.0000055,"caching_price":0.00000688,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.6 is Anthropic's most powerful model yet and the best coding model in the world.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@us-central1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3.1-flash-lite@us","object":"model","created":1778175883,"owned_by":"system","input_price":2.5e-7,"caching_price":8.333e-8,"cached_price":2.5e-8,"output_price":0.0000015,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Flash Lite Preview is the most cost-efficient model in the Gemini family, optimized for high-volume, low-latency tasks. It delivers fast responses with solid quality for everyday use cases including summarization, classification, and simple reasoning.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/gemini-2.5-pro@us-east1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-fable-5@eu","object":"model","created":1781015529,"owned_by":"system","input_price":0.000011,"caching_price":0.00001375,"cached_price":0.0000011,"output_price":0.000055,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-pro@us-west1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash-lite@us-west1","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"caching_price":1.8333e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@europe-west4","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-pro@us-south1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-south1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/claude-sonnet-4","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-3.1-flash-lite@eu","object":"model","created":1778175883,"owned_by":"system","input_price":2.5e-7,"caching_price":8.333e-8,"cached_price":2.5e-8,"output_price":0.0000015,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Flash Lite Preview is the most cost-efficient model in the Gemini family, optimized for high-volume, low-latency tasks. It delivers fast responses with solid quality for everyday use cases including summarization, classification, and simple reasoning.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-3.5-flash@us","object":"model","created":1779225804,"owned_by":"system","input_price":0.0000015,"caching_price":0.000001583,"cached_price":1.5e-7,"output_price":0.000009,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"vertex/deepseek-v3.2","object":"model","created":1773944724,"owned_by":"system","input_price":5.6e-7,"caching_price":0.00000168,"cached_price":5.6e-8,"output_price":0.00000168,"max_output_tokens":65535,"context_window":163840,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek-V3.2 is a model that harmonizes high computational efficiency with superior reasoning and agent performance. DeepSeek's approach is built upon three key technical breakthroughs: DeepSeek Sparse Attention (DSA), scalable reinforcement learning framework, and large scale agentic task synthesis pipeline.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-east1","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/gemini-2.5-flash-image@us-east5","object":"model","created":1758392724,"owned_by":"system","input_price":3e-7,"caching_price":0.0000025,"cached_price":3e-7,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-02T00:00:00Z"},{"api":"chat","id":"vertex/claude-opus-4-6","object":"model","created":1770317868,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.6 is Anthropic's most powerful model yet and the best coding model in the world.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"vertex/claude-sonnet-4@europe-west1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"vertex/gemini-2.5-pro@europe-west1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/xiaomimimo/mimo-v2-flash","object":"model","created":1779873277,"owned_by":"system","input_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Xiaomi MiMo-V2-Flash is a proprietary MoE model developed by Xiaomi, designed for extreme inference efficiency with 309B total parameters (15B active). By incorporating an innovative Hybrid attention architecture and multi-layer MTP inference acceleration, it ranks among the top 2 global open-source models across multiple Agent benchmarks. Its coding capabilities surpass all open-source models and rival the industry-leading closed-source model, Claude 4.5 Sonnet—yet at only 2.5% of the inference","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-r1-turbo","object":"model","created":1738263837,"owned_by":"system","input_price":7e-7,"cached_price":7e-7,"output_price":0.0000025,"max_output_tokens":0,"context_window":64000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 is the latest open-source model released by the DeepSeek team, featuring impressive reasoning capabilities, particularly achieving performance comparable to OpenAI's o1 model in mathematics, coding, and reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/minimax/minimax-m2.7","object":"model","created":1773915388,"owned_by":"system","input_price":3e-7,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-3.2-3b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":3e-8,"cached_price":3e-8,"output_price":5e-8,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out)","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/minimax/minimax-m2.7-highspeed","object":"model","created":1779873246,"owned_by":"system","input_price":6e-7,"output_price":0.0000024,"max_output_tokens":0,"context_window":204800,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"MiniMax M2.7-highspeed is an accelerated SOTA model engineered for scenarios demanding extreme efficiency. It perfectly inherits the core intelligence and robust digital workspace capabilities of the standard M2.7. In real-world software engineering, M2.7 excels by independently driving end-to-end project delivery while efficiently handling advanced tasks such as log analysis, bug troubleshooting, code security, and machine learning. In the professional workspace, it boasts the highest open-sour","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/zai-org/glm-5.1","object":"model","created":1779873283,"owned_by":"system","input_price":0.00000138,"output_price":0.0000044,"max_output_tokens":0,"context_window":204800,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5.1 is Z.AI's latest flagship model, meticulously engineered for long-horizon autonomous tasks. Capable of working continuously on a single assignment for up to 8 hours, it autonomously manages the entire workflow—from initial planning and execution to iterative optimization and the delivery of production-grade results. While its general capabilities and coding proficiency are on par with Claude Opus 4.6, GLM-5.1 excels particularly in sustained execution, complex engineering optimization, a","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-v3-turbo","object":"model","created":1748631837,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.0000013,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 is the latest open-source model released by the DeepSeek team, featuring impressive reasoning capabilities, particularly achieving performance comparable to OpenAI's o1 model in mathematics, coding, and reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/mistralai/mistral-nemo","object":"model","created":1718037161,"owned_by":"system","input_price":1.7e-7,"cached_price":1.7e-7,"output_price":1.7e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/qwen/qwen3-235b-a22b-fp8","object":"model","created":1745882204,"owned_by":"system","input_price":2e-7,"cached_price":2e-7,"output_price":8e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/qwen/qwen-2.5-72b-instruct","object":"model","created":1745882204,"owned_by":"system","input_price":3.8e-7,"cached_price":3.8e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":32000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/inclusionai/ling-2.6-flash","object":"model","created":1779873228,"owned_by":"system","input_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Inclusion AI ling-2.6-flash","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/qwen/qwen3.5-397b-a17b","object":"model","created":1764371804,"owned_by":"system","input_price":6e-7,"cached_price":6e-7,"output_price":0.0000036,"max_output_tokens":65536,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across a variety of tasks—including language understanding, logical reasoning, code generation, agentic tasks, image understanding, video understanding, and graphical user interface (GUI) interaction—it demonstrates exceptional performance comparable to current top-tier frontier models. Possessing robust code generation and agentic capabilities, it exhibits strong generalization across various agent scenarios.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/zai-org/glm-4.5","object":"model","created":1753899508,"owned_by":"system","input_price":6e-7,"cached_price":6e-7,"output_price":0.0000022,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-4.5 is a powerful family of open-source, Mixture-of-Experts (MoE) foundation models designed for complex reasoning, software development, and autonomous intelligent agents.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-v3.2","object":"model","created":1772283132,"owned_by":"system","input_price":2.69e-7,"cached_price":1.345e-7,"output_price":4e-7,"max_output_tokens":65536,"context_window":163840,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-V3.2 is a next-generation foundation model designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance. Built upon DeepSeek Sparse Attention (DSA) for efficient long-context reasoning, a scalable reinforcement learning framework reaching frontier-level performance, and a large-scale agentic task synthesis pipeline for reliable tool-use and multi-step decision-making.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/gryphe/mythomax-l2-13b","object":"model","created":1688259600,"owned_by":"system","input_price":9e-8,"cached_price":9e-8,"output_price":9e-8,"max_output_tokens":0,"context_window":4096,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time).","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-3.1-8b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":5e-8,"cached_price":5e-8,"output_price":5e-8,"max_output_tokens":0,"context_window":16384,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/google/gemma-4-26b-a4b-it","object":"model","created":1779719796,"owned_by":"system","input_price":1.3e-7,"cached_price":1.3e-7,"output_price":4e-7,"max_output_tokens":131072,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemma 4 26B A4B is a Mixture of Experts model from Google DeepMind built for scalable performance with a 256K context window. Supports text and image input, native thinking mode, function calling, structured output, and 140+ languages. Ideal for long context RAG, agentic workflows, coding, and multimodal understanding.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/kwaipilot/kat-coder-pro","object":"model","created":1779873236,"owned_by":"system","input_price":3e-7,"output_price":0.0000012,"max_output_tokens":0,"context_window":256000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"KAT-Coder-Pro V2 by KwaiKAT is a non-reasoning model optimized for agentic coding. It delivers strong performance on reasoning-style tasks while requiring significantly fewer output tokens than peer models. With the 1210 release, it achieved a score of 64 on the Artificial Analysis Intelligence Index, placing it in the global Top 10 and ranking first among all non-reasoning models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-v3-0324","object":"model","created":1748631837,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.0000013,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 is the latest open-source model released by the DeepSeek team, featuring impressive reasoning capabilities, particularly achieving performance comparable to OpenAI's o1 model in mathematics, coding, and reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-prover-v2-671b","object":"model","created":1738263837,"owned_by":"system","input_price":7e-7,"cached_price":7e-7,"output_price":0.0000025,"max_output_tokens":0,"context_window":160000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek_v3","object":"model","created":1748631837,"owned_by":"system","input_price":8.9e-7,"cached_price":8.9e-7,"output_price":8.9e-7,"max_output_tokens":0,"context_window":64000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/microsoft/wizardlm-2-8x22b","object":"model","created":1738865908,"owned_by":"system","input_price":6.2e-7,"cached_price":6.2e-7,"output_price":6.2e-7,"max_output_tokens":0,"context_window":65535,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/inclusionai/ling-2.6-1t","object":"model","created":1779873226,"owned_by":"system","input_price":3e-7,"output_price":0.0000025,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Inclusion AI ling-2.6-1t","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/baichuan/baichuan-m2-32b","object":"model","created":1779873202,"owned_by":"system","input_price":7e-8,"output_price":7e-8,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Baichuan-M2 is a medically-enhanced reasoning model specifically designed for real-world medical reasoning tasks. We begin with real-world medical questions and conduct reinforcement learning training based on a large-scale verifier system. While maintaining the model's general capabilities, the medical effectiveness of Baichuan-M2 has achieved breakthrough improvements.  Baichuan-M2 is currently the world's best open-source medical model. On the HealthBench Benchmark, it surpasses all open-sour","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/sao10k/l31-70b-euryale-v2.2","object":"model","created":1734535928,"owned_by":"system","input_price":0.00000148,"cached_price":0.00000148,"output_price":0.00000148,"max_output_tokens":0,"context_window":16000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/Sao10K/L3-8B-Stheno-v3.2","object":"model","created":1734535928,"owned_by":"system","input_price":5e-8,"cached_price":5e-8,"output_price":5e-8,"max_output_tokens":0,"context_window":8192,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Sao10K/L3-8B-Stheno-v3.2 is a highly skilled actor that excels at fully immersing itself in any role assigned.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-r1-distill-qwen-32b","object":"model","created":1738263837,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":12800,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/qwen/qwen2.5-vl-72b-instruct","object":"model","created":1745882204,"owned_by":"system","input_price":8e-7,"cached_price":8e-7,"output_price":8e-7,"max_output_tokens":0,"context_window":96000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen2 VL 72B is a multimodal LLM from the Qwen Team with the following key enhancements:\n\nSoTA understanding of images of various resolution \u0026 ratio: Qwen2-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.\n\nUnderstanding videos of 20min+: Qwen2-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.\n\nAgent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions.\n\nMultilingual Support: to serve global users, besides English and Chinese, Qwen2-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-r1-distill-qwen-14b","object":"model","created":1738263837,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":1.5e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/moonshotai/kimi-k2-instruct","object":"model","created":1752257908,"owned_by":"system","input_price":5.7e-7,"cached_price":5.7e-7,"output_price":0.0000023,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Kimi K2 Instruct","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-r1-distill-llama-70b","object":"model","created":1738263837,"owned_by":"system","input_price":8e-7,"cached_price":8e-7,"output_price":8e-7,"max_output_tokens":0,"context_window":32000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 Distill LLama 70B","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/zai-org/glm-4.6","object":"model","created":1753899508,"owned_by":"system","input_price":6e-7,"cached_price":6e-7,"output_price":0.0000022,"max_output_tokens":131072,"context_window":204800,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-4.6 is Z AI’s latest flagship model, designed to push agentic and coding performance further. It expands the context window from 128K to 200K tokens, improves reasoning and tool-use capabilities, and delivers stronger results in coding benchmarks and real-world development workflows. GLM-4.6 demonstrates refined writing quality, more capable agent behavior, and higher token efficiency (≈15% fewer tokens vs. GLM-4.5).\n\nEvaluations show clear gains over GLM-4.5 across reasoning, agents, and coding, reaching near parity with Claude Sonnet 4 in practical tasks while outperforming other open-source baselines. GLM-4.6 is available through the Z.ai API platform, OpenRouter, coding agents (Claude Code, Roo Code, Cline, Kilo Code), and soon as downloadable weights on HuggingFace and ModelScope.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","object":"model","created":1738263837,"owned_by":"system","input_price":2e-7,"cached_price":2e-7,"output_price":8.5e-7,"max_output_tokens":1048576,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/sao10k/l3-8b-lunaris","object":"model","created":1734535928,"owned_by":"system","input_price":5e-8,"cached_price":5e-8,"output_price":5e-8,"max_output_tokens":0,"context_window":8192,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"A generalist / roleplaying model merge based on Llama 3.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/baidu/ernie-4.5-300b-a47b-paddle","object":"model","created":1779873209,"owned_by":"system","input_price":2.8e-7,"output_price":0.0000011,"max_output_tokens":0,"context_window":123000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The ERNIE 4.5 series of open-source models adopts a Mixture-of-Experts (MoE) architecture, representing an innovative multimodal heterogeneous model structure. It achieves cross-modal knowledge fusion through a parameter-sharing mechanism while retaining dedicated parameter spaces for individual modalities. This architecture is particularly well-suited for the continuous pre-training paradigm from large language models to multimodal models, significantly enhancing multimodal understanding capabi","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-r1","object":"model","created":1738263837,"owned_by":"system","input_price":0.000004,"cached_price":0.000004,"output_price":0.000004,"max_output_tokens":0,"context_window":64000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek R1 is the latest open-source model released by the DeepSeek team, featuring impressive reasoning capabilities, particularly achieving performance comparable to OpenAI's o1 model in mathematics, coding, and reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-3-8b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":4e-8,"cached_price":4e-8,"output_price":4e-8,"max_output_tokens":0,"context_window":8192,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Meta's latest class of model (Llama 3) launched with a variety of sizes \u0026 flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/tencent/hy3","object":"model","created":1783958717,"owned_by":"system","input_price":0,"output_price":0,"max_output_tokens":262144,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Hy3 is built for real world business scenarios with a 295B total, 21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long form comprehension, multi turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across high frequency interactions and complex workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/xiaomimimo/mimo-v2-pro","object":"model","created":1779873278,"owned_by":"system","input_price":0.000002,"output_price":0.000006,"max_output_tokens":0,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Xiaomi’s MiMo-V2-Pro is a flagship, \u003e1T parameter foundation model with a 1M context window, specifically optimized for advanced agentic workflows. Highly compatible with frameworks like OpenClaw, it secures top-tier global rankings on PinchBench and ClawBench, with a perceived capability approaching Opus 4.6. Built to act as the cognitive core of intelligent systems, MiMo-V2-Pro seamlessly orchestrates complex tasks, drives engineering automation, and consistently delivers dependable real-world","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/GLM-5","object":"model","created":1774005451,"owned_by":"system","input_price":0.000001,"cached_price":2e-7,"output_price":0.0000032,"max_output_tokens":131072,"context_window":202800,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from \"writing code\" to \"building systems,\" it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the \"frontend-heavy, logic-light\" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-3-70b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":5.1e-7,"cached_price":5.1e-7,"output_price":7.4e-7,"max_output_tokens":0,"context_window":8192,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Meta's latest class of model (Llama 3) launched with a variety of sizes \u0026 flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/meta-llama/llama-3.3-70b-instruct","object":"model","created":1738865908,"owned_by":"system","input_price":3.9e-7,"cached_price":3.9e-7,"output_price":3.9e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/inclusionai/ring-2.6-1t","object":"model","created":1779873233,"owned_by":"system","input_price":3e-7,"output_price":0.0000025,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Inclusion AI ring-2.6-1t","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"novita/deepseek/deepseek-v4-flash","object":"model","created":1779873221,"owned_by":"system","input_price":1.4e-7,"output_price":2.8e-7,"max_output_tokens":0,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-V4-Flash is a lightweight model meticulously designed by DeepSeek to deliver the ultimate combination of lightning-fast response times and unmatched cost-effectiveness. Engineered with fewer parameters and significantly lower activation overhead, V4-Flash provides an exceptionally fast and economical API service. At its core, V4-Flash demonstrates outstanding reasoning capabilities that closely rival the V4-Pro model. While featuring a slightly streamlined repository of world knowledge,","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@eu-west-3","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@eu-west-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-haiku-4-5@ap-northeast-1","object":"model","created":1782922333,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"ap"},{"api":"chat","id":"bedrock/claude-sonnet-4-5","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@eu-west-1","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@us-east-2","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-8@eu-central-1","object":"model","created":1780041625,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@eu-west-3","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/kimi-k2.5@us-west-2","object":"model","created":1774966161,"owned_by":"system","input_price":6e-7,"output_price":0.000003,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/minimax-m2.5@eu-west-1","object":"model","created":1780206136,"owned_by":"system","input_price":3.6e-7,"output_price":0.00000144,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-7@eu-west-3","object":"model","created":1776418380,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.7 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.7 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.7 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@us-west-2","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@eu-north-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@us-east-2","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-7@eu-central-1","object":"model","created":1776418380,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.7 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.7 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.7 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/gpt-5.4@us-west-2","object":"model","created":1781625697,"owned_by":"system","input_price":0.00000275,"cached_price":2.75e-7,"output_price":0.0000165,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":true,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-8@eu-west-3","object":"model","created":1780041625,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/minimax-m2.5@us-east-2","object":"model","created":1780206133,"owned_by":"system","input_price":3e-7,"output_price":0.0000012,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@us-west-2","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5@us-west-2","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-7@eu-north-1","object":"model","created":1776418380,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.7 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.7 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.7 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@eu-west-1","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@eu-west-3","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4@us-east-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-7","object":"model","created":1776418380,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.7 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.7 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.7 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/claude-opus-4-8@ap-northeast-1","object":"model","created":1782922327,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"ap"},{"api":"chat","id":"bedrock/claude-opus-4-8@eu-north-1","object":"model","created":1780041625,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@us-west-2","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-6","object":"model","created":1771498893,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/minimax-m2.5@eu-north-1","object":"model","created":1780206136,"owned_by":"system","input_price":3.6e-7,"output_price":0.00000144,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@eu-north-1","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@us-east-1","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5@eu-west-1","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/gpt-5.4@us-east-1","object":"model","created":1781625697,"owned_by":"system","input_price":0.00000275,"cached_price":2.75e-7,"output_price":0.0000165,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":true,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@us-east-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/kimi-k2.5@eu-west-2","object":"model","created":1774966161,"owned_by":"system","input_price":7.2e-7,"caching_price":7.2e-7,"cached_price":7.2e-7,"output_price":0.0000036,"max_output_tokens":16000,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5","object":"model","created":1764627436,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/kimi-k2.5@us-east-1","object":"model","created":1774966161,"owned_by":"system","input_price":6e-7,"output_price":0.000003,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5@us-east-1","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/gpt-5.5@us-east-1","object":"model","created":1781625697,"owned_by":"system","input_price":0.0000055,"cached_price":5.5e-7,"output_price":0.000033,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":true,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5@eu-north-1","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-7@eu-west-1","object":"model","created":1776418380,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.7 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.7 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.7 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/minimax-m2.5@us-west-2","object":"model","created":1780206133,"owned_by":"system","input_price":3e-7,"output_price":0.0000012,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-5","object":"model","created":1782838926,"owned_by":"system","input_price":0.000002,"caching_price":0.0000025,"cached_price":2e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 5 is the latest model in the Sonnet family and an upgrade to Sonnet 4.6, with gains in agentic coding and professional work. It delivers top-tier intelligence at Sonnet pricing, well suited to production agents, high-volume pipelines, and everyday professional work like document drafting, spreadsheet analysis, and presentations.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@us-east-2","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-5@eu-central-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/minimax-m2.5@eu-south-1","object":"model","created":1780206136,"owned_by":"system","input_price":3.6e-7,"output_price":0.00000144,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/minimax-m2.5@us-east-1","object":"model","created":1780206133,"owned_by":"system","input_price":3e-7,"output_price":0.0000012,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-8","object":"model","created":1780041623,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/claude-sonnet-4@us-west-2","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@eu-central-1","object":"model","created":1771498893,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/minimax-m2.5@eu-central-1","object":"model","created":1780206136,"owned_by":"system","input_price":3.6e-7,"output_price":0.00000144,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is MiniMax's latest large language model, delivering strong performance across reasoning, coding, and tool use with improved efficiency for production workloads.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-fable-5@us-east-1","object":"model","created":1781016885,"owned_by":"system","input_price":0.000011,"caching_price":0.00001375,"cached_price":0.0000011,"output_price":0.000055,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.","data_retention":true,"data_retention_days":30,"privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5@eu-west-3","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-6","object":"model","created":1770315610,"owned_by":"system","input_price":0.000005,"caching_price":0.00000625,"cached_price":5e-7,"output_price":0.000025,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.6 is Anthropic's most powerful model yet and the best coding model in the world.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/gpt-5.5@us-east-2","object":"model","created":1781625697,"owned_by":"system","input_price":0.0000055,"cached_price":5.5e-7,"output_price":0.000033,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":true,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-8@eu-west-1","object":"model","created":1780041625,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model, advancing performance across coding, enterprise workflows, and long-running agentic tasks. Coding: Claude Opus 4.8 is built for agentic coding at scale, excelling at long-horizon projects, complex implementations, and polished UI design. It handles the full lifecycle from architecture to deployment, including design-quality UI so senior engineers can delegate complex work with confidence. Enterprise workflows: Claude Opus 4.8 sets the standard for enterprise knowledge work, carrying context across sessions to manage complex, multi-day projects end-to-end. It delivers professional polish on the documents, spreadsheets, and presentations that move work forward.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4@eu-west-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4-6@ap-northeast-1","object":"model","created":1782922165,"owned_by":"system","input_price":0.0000033,"caching_price":0.000004125,"cached_price":3e-7,"output_price":0.0000165,"max_output_tokens":64000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Sonnet 4.6 is Anthropic's best coding model in the world, leading on SWE-bench Verified (77.2%) and OSWorld (61.4%). It delivers sustained autonomous performance on complex tasks for over 30 hours—up from seven hours for Opus 4—maintaining focus and reliability throughout the entire software development lifecycle, with enhanced capabilities in tool handling, memory management, and context processing that make it the strongest model for building complex agents.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"ap"},{"api":"chat","id":"bedrock/kimi-k2.5@us-east-2","object":"model","created":1774966161,"owned_by":"system","input_price":6e-7,"output_price":0.000003,"max_output_tokens":16000,"context_window":128000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/gpt-5.4@us-east-2","object":"model","created":1781625697,"owned_by":"system","input_price":0.00000275,"cached_price":2.75e-7,"output_price":0.0000165,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":true,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/kimi-k2.5@eu-north-1","object":"model","created":1774966161,"owned_by":"system","input_price":7.2e-7,"caching_price":7.2e-7,"cached_price":7.2e-7,"output_price":0.0000036,"max_output_tokens":16000,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-haiku-4-5@eu-central-1","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-haiku-4-5@us-east-2","object":"model","created":1761216302,"owned_by":"system","input_price":0.0000011,"caching_price":0.000001375,"cached_price":1.1e-7,"output_price":0.0000055,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-haiku-4-5","object":"model","created":1761216302,"owned_by":"system","input_price":0.000001,"caching_price":0.00000125,"cached_price":1e-7,"output_price":0.000005,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"global"},{"api":"chat","id":"bedrock/claude-sonnet-4@eu-north-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4@eu-west-3","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4@us-east-2","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"bedrock/claude-opus-4-5@eu-central-1","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-sonnet-4@eu-central-1","object":"model","created":1747933971,"owned_by":"system","input_price":0.000003,"caching_price":0.00000375,"cached_price":3e-7,"output_price":0.000015,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Anthropic's most intelligent model. The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@eu-north-1","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"eu"},{"api":"chat","id":"bedrock/claude-opus-4-5@us-east-1","object":"model","created":1764627436,"owned_by":"system","input_price":0.0000055,"caching_price":0.000006875,"cached_price":5.5e-7,"output_price":0.0000275,"max_output_tokens":64000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Claude Opus 4.5 is Anthropic's flagship AI model, celebrated as an industry leader for complex coding, autonomous agent tasks, and deep analysis. It combines extreme reasoning capabilities with high token efficiency, making multi-day engineering projects and routine office tasks drastically faster and more cost-effective","privacy_comments":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","geolocation":"us"},{"api":"chat","id":"google/gemma-4-31b-it","object":"model","created":1781511896,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":8192,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","data_retention":true,"data_retention_days":30,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"google/gemini-2.5-pro","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"google/gemini-3.1-flash-lite","object":"model","created":1772559935,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.0000015,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Flash Lite Preview is the most cost-efficient model in the Gemini family, optimized for high-volume, low-latency tasks. It delivers fast responses with solid quality for everyday use cases including summarization, classification, and simple reasoning.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"google/gemini-3.1-pro-preview","object":"model","created":1771524000,"owned_by":"system","input_price":0.000002,"caching_price":0.0000045,"cached_price":2e-7,"output_price":0.000012,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Pro is the next iteration in the Gemini 3 series of models, a suite of highly capable, natively multimodal reasoning models. As of this model card’s date of publication, Gemini 3.1 Pro is Google’s most advanced model for complex tasks. Geminin 3.1 Pro can comprehend vast datasets and challenging problems from massively multimodal information sources, including text, audio, images, video, and entire code repositories.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"google/gemini-3-flash-preview","object":"model","created":1766022113,"owned_by":"system","input_price":5e-7,"cached_price":5e-8,"output_price":0.000003,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3 Flash Preview is designed to deliver strong agentic capabilities (near-Pro level) at substantial speed and value. Making it perfect for engaging multi-turn chats, and collaborating back and forth with your coding agent without getting out of flow. Compared to 2.5 Flash it delivers significant improvements across the board.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"google/gemini-2.5-flash","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"google/gemini-3.1-flash-image-preview","object":"model","created":1772125200,"owned_by":"system","input_price":5e-7,"caching_price":0,"cached_price":0,"output_price":0.000002,"max_output_tokens":32768,"context_window":131072,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":true,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 3.1 Flash Image is optimized for image understanding and generation and offers a balance of price and performance.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-06-25T00:00:00Z"},{"api":"chat","id":"google/gemini-3-pro-preview","object":"model","created":1771524000,"owned_by":"system","input_price":0.000002,"caching_price":0.0000045,"cached_price":2e-7,"output_price":0.000012,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemini 3.1 Pro is the next iteration in the Gemini 3 series of models, a suite of highly capable, natively multimodal reasoning models. As of this model card’s date of publication, Gemini 3.1 Pro is Google’s most advanced model for complex tasks. Geminin 3.1 Pro can comprehend vast datasets and challenging problems from massively multimodal information sources, including text, audio, images, video, and entire code repositories.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"google/gemini-2.5-flash-lite","object":"model","created":1747765524,"owned_by":"system","input_price":1e-7,"cached_price":1e-8,"output_price":4e-7,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Google's smallest and most cost effective model, built for at scale usage.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"groq/openai/gpt-oss-20b","object":"model","created":1754414204,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":5e-7,"max_output_tokens":32768,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"OpenAI's gpt-oss-20b is a 21-billion parameter, open-weight reasoning model released under the Apache 2.0 license. Designed for local execution on consumer hardware and low-latency workflows, it delivers reasoning capabilities and benchmark performance comparable to the OpenAI o3-mini models.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"groq/openai/gpt-oss-120b","object":"model","created":1754414204,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":7.5e-7,"max_output_tokens":32768,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"OpenAI's gpt-oss-120b is a powerful open-weight Large Language Model (LLM) designed for advanced chain-of-thought reasoning, agentic workflows, and complex tool-calling.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"perplexity/sonar-reasoning-pro","object":"model","created":1741313308,"owned_by":"system","input_price":0.000002,"cached_price":0.000002,"output_price":0.000008,"max_output_tokens":8192,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"Premier reasoning offering powered by DeepSeek R1 with Chain of Thought (CoT).","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"perplexity/sonar-pro","object":"model","created":1741313308,"owned_by":"system","input_price":0.000003,"cached_price":0.000003,"output_price":0.000015,"max_output_tokens":8192,"context_window":204800,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"Premier search offering with search grounding, supporting advanced queries and follow-ups.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"perplexity/sonar","object":"model","created":1741313308,"owned_by":"system","input_price":0.000001,"cached_price":0.000001,"output_price":0.000001,"max_output_tokens":8192,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"Lightweight offering with search grounding, quicker and cheaper than Sonar Pro.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nvidia/nemotron-3.5-content-safety","object":"model","created":1781510650,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":8192,"context_window":131072,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens. Suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. Part of the NVIDIA Nemotron family of open models for agentic AI.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"NVIDIA API Trial Terms of Service apply.","geolocation":"global"},{"api":"chat","id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":20480,"context_window":131072,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Nano Omni 30B-A3B (reasoning) is a multimodal MoE model unifying video, audio, image, and text understanding for enterprise Q\u0026A, summarization, transcription, OCR, GUI automation, and document intelligence. Supports chain-of-thought reasoning, tool calling, and up to 256k context.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"NVIDIA API Trial Terms of Service apply.","geolocation":"global"},{"api":"chat","id":"nvidia/nemotron-3-nano-30b-a3b","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Nano 30B-A3B is a small language MoE model offering high compute efficiency and accuracy for building specialized agentic AI systems. Fully open weights, datasets, and recipes. Text in/out, up to 256K context.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"NVIDIA API Trial Terms of Service apply.","geolocation":"global"},{"api":"chat","id":"nvidia/nemotron-3-super-120b-a12b","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":65536,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid Mamba-Transformer MoE model activating just 12B parameters, with multi-token prediction for high throughput. 1M token context for long-horizon agent coherence, cross-document reasoning, and multi-step planning. Strong on AIME 2025, TerminalBench, and SWE-Bench Verified. Part of the NVIDIA Nemotron family.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"NVIDIA API Trial Terms of Service apply.","geolocation":"global"},{"api":"chat","id":"nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1781014014,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":65536,"context_window":1048576,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Ultra is an open frontier reasoning and orchestration model with 55B active parameters out of 550B total (hybrid Transformer-Mamba MoE). Text input/output with up to 1M context, built for long-running agentic workflows: agent orchestration, coding agents, deep research, and complex enterprise tasks. Strong at multi-step reasoning and planning with high-throughput inference. Part of the NVIDIA Nemotron family.","data_retention":true,"data_retention_days":30,"data_used_for_training":true,"privacy_comments":"NVIDIA API Trial Terms of Service apply.","geolocation":"global"},{"api":"chat","id":"openai/o1:low","object":"model","created":1734459999,"owned_by":"system","input_price":0.000015,"cached_price":0.0000075,"output_price":0.00006,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o4-mini:medium","object":"model","created":1744824542,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-mini","object":"model","created":1754586319,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o3-mini:medium","object":"model","created":1738351721,"owned_by":"system","input_price":0.0000011,"cached_price":5.5e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4o","object":"model","created":1732127594,"owned_by":"system","input_price":0.0000025,"cached_price":0.00000125,"output_price":0.00001,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance \u0026 readability. It’s also better at working with uploaded files, providing deeper insights \u0026 more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.6-luna","object":"model","created":1783625420,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai/o3-mini:low","object":"model","created":1738351721,"owned_by":"system","input_price":0.0000011,"cached_price":5.5e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4o-2024-05-13","object":"model","created":1732127594,"owned_by":"system","input_price":0.0000025,"cached_price":0.0000025,"output_price":0.00001,"max_output_tokens":4096,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance \u0026 readability. It’s also better at working with uploaded files, providing deeper insights \u0026 more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","data_retention":true,"privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"openai/gpt-5.4","object":"model","created":1772745445,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o4-mini:high","object":"model","created":1744824542,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o3:flex","object":"model","created":1744827057,"owned_by":"system","input_price":0.000001,"cached_price":2.5e-7,"output_price":0.000004,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"O3 Flex is a cheaper version of the o3 model","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4o-mini","object":"model","created":1721264400,"owned_by":"system","input_price":1.5e-7,"cached_price":7.5e-8,"output_price":6e-7,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4.1-nano","object":"model","created":1744654969,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o1:high","object":"model","created":1734459999,"owned_by":"system","input_price":0.000015,"cached_price":0.0000075,"output_price":0.00006,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4o-2024-08-06","object":"model","created":1732127594,"owned_by":"system","input_price":0.0000025,"cached_price":0.00000125,"output_price":0.00001,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance \u0026 readability. It’s also better at working with uploaded files, providing deeper insights \u0026 more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o4-mini","object":"model","created":1744824542,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o1","object":"model","created":1734459999,"owned_by":"system","input_price":0.000015,"cached_price":0.0000075,"output_price":0.00006,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4.1","object":"model","created":1744654985,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-mini:priority","object":"model","created":1754586506,"owned_by":"system","input_price":4.5e-7,"cached_price":4.5e-8,"output_price":0.0000036,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-nano","object":"model","created":1754586455,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4o-2024-11-20","object":"model","created":1732127594,"owned_by":"system","input_price":0.0000025,"cached_price":0.00000125,"output_price":0.00001,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance \u0026 readability. It’s also better at working with uploaded files, providing deeper insights \u0026 more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.2-chat","object":"model","created":1766164106,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT‑5.2 sets a new state of the art across many benchmarks, including GDPval, where it outperforms industry professionals at well-specified knowledge work tasks spanning 44 occupations.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.6-sol","object":"model","created":1783625420,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.4-nano","object":"model","created":1773832106,"owned_by":"system","input_price":2e-7,"cached_price":2e-8,"output_price":0.00000125,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5:flex","object":"model","created":1754586506,"owned_by":"system","input_price":6.25e-7,"cached_price":6.25e-8,"output_price":0.000005,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o4-mini:flex","object":"model","created":1744824542,"owned_by":"system","input_price":5.5e-7,"cached_price":1.38e-7,"output_price":0.0000022,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o1:medium","object":"model","created":1734459999,"owned_by":"system","input_price":0.000015,"cached_price":0.0000075,"output_price":0.00006,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.1-chat","object":"model","created":1764610091,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 Chat points to the GPT-5.1 snapshot currently used in ChatGPT. We recommend GPT-5.1 for most API usage, but feel free to use this GPT-5.1 Chat model to test our latest improvements for chat use cases.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5","object":"model","created":1754586506,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o3-mini","object":"model","created":1738351721,"owned_by":"system","input_price":0.0000011,"cached_price":5.5e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o3-mini:high","object":"model","created":1738351721,"owned_by":"system","input_price":0.0000011,"cached_price":5.5e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o3","object":"model","created":1744827057,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/o4-mini:low","object":"model","created":1744824542,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-4.1-mini","object":"model","created":1744654981,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.6-terra","object":"model","created":1783625420,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.2","object":"model","created":1765472906,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The best model for coding and agentic tasks across industries","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.1","object":"model","created":1754586506,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.5","object":"model","created":1777109681,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-chat","object":"model","created":1754586506,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.3-chat","object":"model","created":1773832106,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly reduces unnecessary refusals, caveats, and overly cautious phrasing that can interrupt conversational flow.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5.4-mini","object":"model","created":1773832106,"owned_by":"system","input_price":7.5e-7,"cached_price":7.5e-8,"output_price":0.0000045,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5:priority","object":"model","created":1754586506,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.00002,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-mini:flex","object":"model","created":1754586319,"owned_by":"system","input_price":1.25e-7,"cached_price":1.25e-8,"output_price":0.000001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai/gpt-5-nano:flex","object":"model","created":1754586455,"owned_by":"system","input_price":2.5e-8,"cached_price":2.5e-9,"output_price":2e-7,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"tensorx/deepseek-v4-flash","object":"model","created":1782554935,"owned_by":"system","input_price":1.5e-7,"cached_price":4e-8,"output_price":3e-7,"max_output_tokens":1048576,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek V4 Flash is an efficiency optimized Mixture of Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M token context window. It is built for fast inference and high throughput workloads while keeping strong reasoning and coding performance. The model uses hybrid attention for efficient long context processing. Reasoning efforts high and xhigh are supported, with xhigh mapping to max reasoning. It is well suited for coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency matter.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"tensorx/deepseek-v4-pro","object":"model","created":1782554943,"owned_by":"system","input_price":0.00000175,"cached_price":4.4e-7,"output_price":0.0000035,"max_output_tokens":1048576,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek V4 Pro is a large scale Mixture of Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M token context window. It is built for advanced reasoning, coding, and long horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it adds a hybrid attention system for efficient long context processing. Reasoning efforts high and xhigh are supported, with xhigh mapping to max reasoning. It is well suited for complex workloads such as full codebase analysis, multi step automation, and large scale information synthesis, where both capability and efficiency are critical.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"tensorx/kimi-k2.7-code","object":"model","created":1782554949,"owned_by":"system","input_price":0.00000125,"cached_price":3.1e-7,"output_price":0.0000045,"max_output_tokens":262144,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.7 Code is a coding focused model in Moonshot AI Kimi K2 family, built to complete end to end programming tasks reliably over long contexts. It uses a native multimodal mixture of experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi turn conversations. With a 256K token context window, it targets long horizon coding, agentic task decomposition, and multi turn dialogue. The model activates 32B parameters out of roughly 1T total.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"tensorx/glm-5.2","object":"model","created":1782554954,"owned_by":"system","input_price":0.0000015,"cached_price":3.8e-7,"output_price":0.0000045,"max_output_tokens":1048576,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GLM 5.2 is the latest Z.ai flagship model for long horizon coding, reasoning, and agentic workflows. It improves on GLM 5.1 with a 1M token context window, stronger engineering task performance, multiple thinking effort levels, and architectural changes that reduce long context inference cost while improving speculative decoding. Released under the MIT license, it is designed for sustained work over large repositories, complex tool use, and multi step technical tasks.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"tensorx/minimax-m3","object":"model","created":1782554635,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.000002,"max_output_tokens":1048576,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M3 is a frontier multimodal model with a 1M token context window built on MiniMax Sparse Attention (MSA). It delivers frontier level performance on coding and agentic tasks, outperforming GPT 5.5 and Gemini 3.1 Pro on SWE Bench Pro and approaching Claude Opus 4.7. It natively handles image and video input and is the first open weight model to combine frontier coding, ultra long context, and native multimodality.","privacy_comments":"No training on user data","geolocation":"eu"},{"api":"chat","id":"coding/gemini-2.5-flash@europe-north1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@us-east1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@europe-west4","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@europe-west8","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@us-central1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@us-west1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@europe-west4","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@us-central1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@us-east5","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@europe-west1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@us-east5","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@europe-central2","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@europe-west8","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@us-south1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@us-west1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@europe-north1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-pro@europe-west1","object":"model","created":1746582113,"owned_by":"system","input_price":0.00000125,"caching_price":0.000002375,"cached_price":3.1e-7,"output_price":0.00001,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":true,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@us-east1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@us-south1","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"coding/gemini-2.5-flash@europe-central2","object":"model","created":1747765524,"owned_by":"system","input_price":3e-7,"caching_price":5.5e-7,"cached_price":7.5e-8,"output_price":0.0000025,"max_output_tokens":65535,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google's first hybrid reasoning model which supports a 1M token context window and has thinking budgets. Most balanced Gemini model, optimized for low latency use cases.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-16T00:00:00Z"},{"api":"chat","id":"openai-responses/gpt-5.1","object":"model","created":1771606800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 is our flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/o3-mini","object":"model","created":1738351721,"owned_by":"system","input_price":0.0000011,"cached_price":5.5e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-4.1","object":"model","created":1744654985,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.3-chat","object":"model","created":1773832106,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":16384,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly reduces unnecessary refusals, caveats, and overly cautious phrasing that can interrupt conversational flow.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.2-codex","object":"model","created":1764719016,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.2-Codex is a version of GPT-5.2 optimized for agentic coding tasks in Codex or similar environments","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.6-luna","object":"model","created":1783669186,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.4-mini","object":"model","created":1773832106,"owned_by":"system","input_price":7.5e-7,"cached_price":7.5e-8,"output_price":0.0000045,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.6-terra","object":"model","created":1783669186,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.3-codex","object":"model","created":1772010000,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5-codex","object":"model","created":1758711928,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5-pro","object":"model","created":1759748728,"owned_by":"system","input_price":0.000015,"cached_price":0.000015,"output_price":0.00012,"max_output_tokens":272000,"context_window":400000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 Pro is OpenAI’s extended-reasoning tier of GPT-5, built to push reliability on hard problems, long tool chains, and agentic workflows. It keeps GPT-5’s multimodal skills and very large context (API page lists up to 400K tokens) while allocating more compute to think longer and plan better, improving code generation, math, and complex writing beyond standard GPT-5/“Thinking.” OpenAI positions Pro as the version that “uses extended reasoning for even more comprehensive and accurate answers,” targeting high-stakes tasks and enterprise use.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5-nano","object":"model","created":1754586455,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.6-sol","object":"model","created":1783669186,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","data_retention":true,"data_retention_days":30,"privacy_comments":"No training on customer data. Data retained for 30 days.","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.2","object":"model","created":1765472906,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The best model for coding and agentic tasks across industries","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.4-pro","object":"model","created":1765472906,"owned_by":"system","input_price":0.00003,"cached_price":0.00003,"output_price":0.00018,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.1-codex","object":"model","created":1764719016,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.5","object":"model","created":1777109681,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/o3-pro","object":"model","created":1749601952,"owned_by":"system","input_price":0.00002,"cached_price":0.00002,"output_price":0.00008,"max_output_tokens":100000,"context_window":200000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The o3 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-4.1-mini","object":"model","created":1744654981,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5-mini","object":"model","created":1754586319,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-4.1-nano","object":"model","created":1744654969,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.5-pro","object":"model","created":1777109483,"owned_by":"system","input_price":0.00003,"output_price":0.00018,"max_output_tokens":128000,"context_window":1050000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 Pro is OpenAI's high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.4-nano","object":"model","created":1773832106,"owned_by":"system","input_price":2e-7,"cached_price":2e-8,"output_price":0.00000125,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5","object":"model","created":1754586506,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/gpt-5.4","object":"model","created":1772799588,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.\n","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"openai-responses/o4-mini","object":"model","created":1744824542,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"mistral/mistral-small-2503","object":"model","created":1782736388,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Mistral Small 3.1 (2503) is a powerful 24-billion parameter multimodal AI model developed by Mistral AI that processes both text and image inputs. Designed for enterprise efficiency and fast-response agents, it is highly sought after for its exceptional long-context processing, function calling, and local deployment capabilities. ","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-07-31T00:00:00Z"},{"api":"chat","id":"mistral/leanstral-1-5","object":"model","created":1783114058,"owned_by":"system","input_price":0,"cached_price":0,"output_price":0,"max_output_tokens":32768,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/devstral-small-latest","object":"model","created":1782736388,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"mistral-large-latest is the routing tag used by Mistral AI to point to their most advanced flagship small language model","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/devstral-medium-2507","object":"model","created":1782736388,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.000002,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Devstral Medium 2507 is a powerful enterprise-grade AI model developed by Mistral AI, specifically optimized for software engineering and agentic coding tasks.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-07-31T00:00:00Z"},{"api":"chat","id":"mistral/devstral-latest","object":"model","created":1782736388,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.000002,"max_output_tokens":0,"context_window":256000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/devstral-small-2507","object":"model","created":1782736388,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Devstral-Small-2507 (also known as Devstral Small 1.1) is a lightweight 24-billion parameter open-weights model developed by Mistral AI in collaboration with All Hands AI. Built specifically for autonomous software engineering and agentic coding workflows, it is renowned for its ability to edit multiple files, explore complex codebases, and execute tools flawlessly. ","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-07-31T00:00:00Z"},{"api":"chat","id":"mistral/mistral-large-latest","object":"model","created":1782736388,"owned_by":"system","input_price":5e-7,"cached_price":5e-7,"output_price":0.0000015,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"mistral-large-latest is the routing tag used by Mistral AI to point to their most advanced flagship large language model","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/open-mistral-7b","object":"model","created":1782736388,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-7,"output_price":2.5e-7,"max_output_tokens":0,"context_window":32768,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"OpenMistral-7B (officially Mistral 7B) is a highly efficient, 7.3-billion parameter open-weight language model released by Mistral AI. Praised for its excellent performance-to-size ratio, it frequently outperforms much larger proprietary and open-source models while being light enough to run on standard consumer hardware. ","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-08-31T00:00:00Z"},{"api":"chat","id":"mistral/mistral-small-latest","object":"model","created":1782736388,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":6e-7,"max_output_tokens":0,"context_window":256000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Mistral's powerful hybrid model unifying instruct, reasoning, and coding capabilities in a single model. 119B parameters with 6.5B active.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/mistral-small-2603","object":"model","created":1782736388,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":6e-7,"max_output_tokens":0,"context_window":256000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Mistral's powerful hybrid model unifying instruct, reasoning, and coding capabilities in a single model. 119B parameters with 6.5B active.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/mistral-medium-3-5","object":"model","created":1782736388,"owned_by":"system","input_price":0.0000015,"cached_price":0.0000015,"output_price":0.0000075,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/codestral-latest","object":"model","created":1782736388,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":9e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Codestral-latest is Mistral AI’s state-of-the-art open-weight language model built specifically for software development and code generation. It is fine-tuned to assist developers with code generation, completion, refactoring, and debugging across more than 80 programming languages.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/mistral-medium-latest","object":"model","created":1782736388,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.000002,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"mistral-large-latest is the routing tag used by Mistral AI to point to their most advanced flagship medium language model","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"mistral/pixtral-large-latest","object":"model","created":1782736388,"owned_by":"system","input_price":0.000002,"cached_price":0.000002,"output_price":0.000005,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Pixtral-large-latest is Mistral AI’s frontier-class multimodal model. Combining a powerful language backbone with advanced vision capabilities, it excels at visual reasoning, complex chart and document analysis, and native function calling. It supports a massive 128,000-token context window, allowing users to process large amounts of text and multiple high-resolution images seamlessly.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"minimaxi/minimax-m3","object":"model","created":1780298562,"owned_by":"system","input_price":3e-7,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":128000,"context_window":1000000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M3 is a frontier multimodal model with a 1M-token context window built on MiniMax Sparse Attention (MSA). It reaches frontier-level performance on coding and agentic tasks, surpassing GPT-5.5 and Gemini 3.1 Pro on SWE-Bench Pro and approaching Claude Opus 4.7. It natively supports image and video input and is the first open-weight model to combine frontier coding, ultra-long context, and native multimodality.","privacy_comments":"https://platform.minimax.io/docs/guides/text-generation","geolocation":"global"},{"api":"chat","id":"minimaxi/MiniMax-M2.5-highspeed","object":"model","created":1770891388,"owned_by":"system","input_price":6e-7,"caching_price":0.0000024,"cached_price":6e-8,"output_price":0.0000024,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"minimaxi/MiniMax-M2","object":"model","created":1761646588,"owned_by":"system","input_price":3e-7,"caching_price":0.0000012,"cached_price":3e-7,"output_price":0.0000012,"max_output_tokens":128000,"context_window":200000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"minimaxi/MiniMax-M2.7","object":"model","created":1773915388,"owned_by":"system","input_price":3e-7,"caching_price":0.0000012,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"minimaxi/MiniMax-M2.7-highspeed","object":"model","created":1773915388,"owned_by":"system","input_price":6e-7,"caching_price":0.0000012,"cached_price":6e-8,"output_price":0.0000024,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"minimaxi/MiniMax-M2.5","object":"model","created":1770891388,"owned_by":"system","input_price":3e-7,"caching_price":0.0000012,"cached_price":6e-8,"output_price":0.0000012,"max_output_tokens":128000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepseek/deepseek-v4-pro","object":"model","created":1777029550,"owned_by":"system","input_price":4.35e-7,"cached_price":1.45e-8,"output_price":8.7e-7,"max_output_tokens":384000,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":false,"description":"DeepSeek v4 Pro - 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.","data_retention":true,"privacy_comments":"No online information","geolocation":"global"},{"api":"chat","id":"deepseek/deepseek-reasoner","object":"model","created":1738263837,"owned_by":"system","input_price":1.4e-7,"cached_price":2.8e-8,"output_price":2.8e-7,"max_output_tokens":384000,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":false,"description":"An alias for DeepSeek v4 Flash in thinking mode.","data_retention":true,"privacy_comments":"No online information","geolocation":"global","retires_at":"2026-07-24T00:00:00Z"},{"api":"chat","id":"deepseek/deepseek-chat","object":"model","created":1738263837,"owned_by":"system","input_price":1.4e-7,"cached_price":2.8e-8,"output_price":2.8e-7,"max_output_tokens":384000,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":false,"description":"An alias for DeepSeek v4 Flash in non-thinking mode.","data_retention":true,"privacy_comments":"No online information","geolocation":"global","retires_at":"2026-07-24T00:00:00Z"},{"api":"chat","id":"deepseek/deepseek-v4-flash","object":"model","created":1777029550,"owned_by":"system","input_price":1.4e-7,"cached_price":2.8e-9,"output_price":2.8e-7,"max_output_tokens":384000,"context_window":1000000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":false,"description":"DeepSeek v4 Flash - 284B total / 13B active params. Your fast, efficient, and economical choice.","data_retention":true,"privacy_comments":"No online information","geolocation":"global"},{"api":"chat","id":"deepinfra/ByteDance/Seed-2.0-pro","object":"model","created":1779873106,"owned_by":"system","input_price":5e-7,"cached_price":1e-7,"output_price":0.000003,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3.5-27B","object":"model","created":1779873132,"owned_by":"system","input_price":2.6e-7,"output_price":0.0000026,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","object":"model","created":1753454294,"owned_by":"system","input_price":4e-7,"cached_price":4e-7,"output_price":0.0000016,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3-Coder-480B-A35B-Instruct is Alibaba’s flagship open-weight AI model designed for autonomous software development and agentic workflows. Using a sparse Mixture-of-Experts (MoE) architecture, it achieves state-of-the-art coding performance that regularly rivals or outperforms proprietary models like Claude Sonnet. ","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-32B","object":"model","created":1745882204,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":40000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/google/gemma-4-26B-A4B-it","object":"model","created":1779719796,"owned_by":"system","input_price":7e-8,"cached_price":7e-8,"output_price":3.4e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemma 4 26B A4B is a Mixture of Experts model from Google DeepMind built for scalable performance with a 256K context window. Supports text and image input, native thinking mode, function calling, and 140+ languages. Ideal for long context RAG, agentic workflows, coding, and multimodal understanding.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","object":"model","created":1779873116,"owned_by":"system","input_price":2.3e-7,"cached_price":2e-7,"output_price":0.0000023,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/ByteDance/Seed-2.0-mini","object":"model","created":1779873104,"owned_by":"system","input_price":1e-7,"cached_price":2e-8,"output_price":4e-7,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Built for low-latency, high-concurrency, cost-sensitive use cases, with flexible deployment, four-tier thinking, and multimodal","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-235B-A22B","object":"model","created":1745882204,"owned_by":"system","input_price":2e-7,"cached_price":2e-7,"output_price":6e-7,"max_output_tokens":4096,"context_window":40000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/google/gemma-4-31B-it","object":"model","created":1779873160,"owned_by":"system","input_price":1.3e-7,"output_price":3.8e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","object":"model","created":1745882204,"owned_by":"system","input_price":2.3e-7,"cached_price":2.3e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3.5-35B-A3B","object":"model","created":1779873137,"owned_by":"system","input_price":1.4e-7,"cached_price":5e-8,"output_price":0.000001,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3.5-397B-A17B","object":"model","created":1779873138,"owned_by":"system","input_price":4.9e-7,"cached_price":3e-7,"output_price":0.0000036,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","object":"model","created":1779873148,"owned_by":"system","input_price":0.000001,"cached_price":2e-7,"output_price":0.000003,"max_output_tokens":0,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in [MiMo-V2-Flash](https://github.com/XiaomiMiMo/MiMo-V2-Flash).","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","object":"model","created":1715697754,"owned_by":"system","input_price":2e-8,"cached_price":2e-8,"output_price":5e-8,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":false,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-R1","object":"model","created":1738263837,"owned_by":"system","input_price":8.5e-7,"cached_price":8.5e-7,"output_price":0.0000025,"max_output_tokens":8192,"context_window":64000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-R1 is an advanced, open-weights reasoning model by DeepSeek. Designed to compete with flagship reasoning models like OpenAI's o1, it focuses heavily on complex problem-solving in mathematics, coding, and science by \"thinking\" before it speaks, natively outputting a detailed, step-by-step chain of thought.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","object":"model","created":1738263837,"owned_by":"system","input_price":2.3e-7,"cached_price":2.3e-7,"output_price":6.9e-7,"max_output_tokens":8192,"context_window":64000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"DeepSeek-R1-Distill-Llama-70B is an open-weights, 70-billion parameter language model developed by DeepSeek. It distills the advanced mathematical, coding, and logical reasoning patterns of the flagship DeepSeek-R1 model into the highly optimized Llama-3.3-70B-Instruct architecture.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/zai-org/GLM-5.1","object":"model","created":1779873198,"owned_by":"system","input_price":0.00000105,"cached_price":2.05e-7,"output_price":0.0000035,"max_output_tokens":0,"context_window":202752,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","object":"model","created":1779873155,"owned_by":"system","input_price":1e-7,"cached_price":2e-8,"output_price":2e-7,"max_output_tokens":0,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/microsoft/phi-4","object":"model","created":1746134561,"owned_by":"system","input_price":7e-8,"cached_price":7e-8,"output_price":1.4e-7,"max_output_tokens":0,"context_window":16384,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.\n\nWhile it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct","object":"model","created":1745882204,"owned_by":"system","input_price":7e-8,"cached_price":7e-8,"output_price":1.6e-7,"max_output_tokens":0,"context_window":16384,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/XiaomiMiMo/MiMo-V2.5","object":"model","created":1779873145,"owned_by":"system","input_price":4e-7,"cached_price":8e-8,"output_price":0.000002,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture. Built upon the MiMo-V2-Flash backbone and extended with dedicated vision and audio encoders, it delivers robust performance across multimodal perception, long-context reasoning, and agentic workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","object":"model","created":1779873120,"owned_by":"system","input_price":3e-7,"cached_price":1e-7,"output_price":0.000001,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/ByteDance/Seed-1.8","object":"model","created":1779873100,"owned_by":"system","input_price":2.5e-7,"cached_price":5e-8,"output_price":0.000002,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/ByteDance/Seed-2.0-code","object":"model","created":1779873102,"owned_by":"system","input_price":5e-7,"cached_price":1e-7,"output_price":0.000003,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct","object":"model","created":1738865908,"owned_by":"system","input_price":3.5e-7,"cached_price":3.5e-7,"output_price":4e-7,"max_output_tokens":4096,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-V3","object":"model","created":1738263837,"owned_by":"system","input_price":8.5e-7,"cached_price":8.5e-7,"output_price":9e-7,"max_output_tokens":8192,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","object":"model","created":1738865908,"owned_by":"system","input_price":2.3e-7,"cached_price":2.3e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct","object":"model","created":1738865908,"owned_by":"system","input_price":8e-7,"cached_price":8e-7,"output_price":8e-7,"max_output_tokens":0,"context_window":130815,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":false,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","object":"model","created":1779873184,"owned_by":"system","input_price":5e-8,"output_price":2e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces compu","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-Max","object":"model","created":1779873122,"owned_by":"system","input_price":0.0000012,"cached_price":2.4e-7,"output_price":0.000006,"max_output_tokens":0,"context_window":256000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The latest flagship model in the Qwen family. State-of-the-art results across a comprehensive suite of benchmarks — including knowledge, reasoning, coding, instruction following, human preference alignment, agent tasks, and multilingual understanding.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-V3.1","object":"model","created":1756232308,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":0.000001,"max_output_tokens":0,"context_window":163840,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek-V3.1 by DeepSeek-AI is a state-of-the-art, hybrid-inference artificial intelligence model that allows users to toggle between fast conversational responses and deep logical reasoning modes within a single architecture.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","object":"model","created":1779873179,"owned_by":"system","input_price":1e-7,"output_price":5e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","object":"model","created":1738865908,"owned_by":"system","input_price":1.2e-7,"cached_price":1.2e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Kimi K2.5","object":"model","created":1774953861,"owned_by":"system","input_price":4.5e-7,"cached_price":7e-8,"output_price":0.00000225,"max_output_tokens":131072,"context_window":262100,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro","object":"model","created":1779873157,"owned_by":"system","input_price":0.0000013,"cached_price":1e-7,"output_price":0.0000026,"max_output_tokens":0,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/moonshotai/Kimi-K2.6","object":"model","created":1779873171,"owned_by":"system","input_price":7.5e-7,"cached_price":1.5e-7,"output_price":0.0000035,"max_output_tokens":0,"context_window":262144,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/zai-org/GLM-4.5","object":"model","created":1753899508,"owned_by":"system","input_price":6e-7,"cached_price":6e-7,"output_price":0.0000022,"max_output_tokens":4096,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3.5-2B","object":"model","created":1779873134,"owned_by":"system","input_price":2e-8,"output_price":1e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and efficient multilingual deployments.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/MiniMaxAI/MiniMax-M2.5","object":"model","created":1779873111,"owned_by":"system","input_price":1.5e-7,"cached_price":3e-8,"output_price":0.00000115,"max_output_tokens":0,"context_window":196608,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"MiniMax M2.5 is SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks, boasting scores of 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp (with context management).","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","object":"model","created":1779873115,"owned_by":"system","input_price":7.1e-8,"output_price":1e-7,"max_output_tokens":0,"context_window":262144,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen3-235B-A22B-Instruct-2507 is the updated version of the Qwen3-235B-A22B non-thinking mode, featuring Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"deepinfra/zai-org/GLM-4.5-Air","object":"model","created":1753899508,"owned_by":"system","input_price":2e-7,"cached_price":2e-7,"output_price":0.0000011,"max_output_tokens":4096,"context_window":131072,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":true,"description":"The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","object":"model","created":1738865908,"owned_by":"system","input_price":2.3e-7,"cached_price":2.3e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":130815,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"global"},{"api":"chat","id":"xiaomi/mimo-v2.5-pro","object":"model","created":1782123109,"owned_by":"system","input_price":4.35e-7,"cached_price":3.6e-9,"output_price":8.7e-7,"max_output_tokens":131072,"context_window":1048576,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Xiaomi MiMo v2.5 Pro. 1M token context window, 128K max output. OpenAI-compatible.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"xiaomi/mimo-v2.5","object":"model","created":1782123109,"owned_by":"system","input_price":1.4e-7,"cached_price":2.8e-9,"output_price":2.8e-7,"max_output_tokens":131072,"context_window":1048576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Xiaomi MiMo v2.5. Native omni-modal model: text, image, video, and audio input, text output. 1M context window for multimodal agent scenarios. OpenAI-compatible.","data_retention":true,"privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/gpt-4.1@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.6-terra@swedencentral","object":"model","created":1783669635,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.5@swedencentral","object":"model","created":1776988800,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-luna@swedencentral","object":"model","created":1783669415,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-nano@swedencentral","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"azure/gpt-5","object":"model","created":1754524800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/openai-responses/gpt-5.4@eastus2","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.\n","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.4@swedencentral","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT 5.4 is OpenAI's frontier model designed for complex professional workloads, with strong reasoning, high reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1-nano","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/gpt-4.1-mini@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1-mini@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5-mini","object":"model","created":1754524800,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-mini@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5@eastus2","object":"model","created":1754524800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-nano@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"azure/gpt-5.4-mini@eastus2","object":"model","created":1773705600,"owned_by":"system","input_price":7.5e-7,"cached_price":7.5e-8,"output_price":0.0000045,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-5.5@eastus2","object":"model","created":1776988800,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/o4-mini@francecentral","object":"model","created":1745452800,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1@uksouth","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/o4-mini@eastus2","object":"model","created":1745452800,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.1@swedencentral","object":"model","created":1764178142,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-terra@swedencentral","object":"model","created":1783669415,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5-nano","object":"model","created":1754524800,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/gpt-5.2-codex@eastus2","object":"model","created":1769088542,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"OpenAI's most intelligent coding model optimized for long-horizon, agentic coding tasks.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-5.5@swedencentral","object":"model","created":1776988800,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/o4-mini@swedencentral","object":"model","created":1745452800,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.4@francecentral","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.\n","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-terra@eastus2","object":"model","created":1783669623,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-luna@eastus2","object":"model","created":1783669623,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.5@eastus2","object":"model","created":1776988800,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4o-mini@swedencentral","object":"model","created":1752861600,"owned_by":"system","input_price":1.5e-7,"cached_price":7.5e-8,"output_price":6e-7,"max_output_tokens":16000,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4o mini is a fast, affordable small model for lightweight tasks. Supports vision, tools, and caching.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5@uksouth","object":"model","created":1754524800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1@swedencentral","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/o4-mini@westus3","object":"model","created":1745452800,"owned_by":"system","input_price":0.0000011,"cached_price":2.75e-7,"output_price":0.0000044,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4o-mini@eastus2","object":"model","created":1752861600,"owned_by":"system","input_price":1.5e-7,"cached_price":7.5e-8,"output_price":6e-7,"max_output_tokens":16000,"context_window":128000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4o mini is a fast, affordable small model for lightweight tasks. Supports vision, tools, and caching.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-4.1@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.6-terra@eastus2","object":"model","created":1783669626,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-5.4@swedencentral","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.\n","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-mini@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5@swedencentral","object":"model","created":1754524800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.1@eastus2","object":"model","created":1764178142,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1-nano@uksouth","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.6-luna@eastus2","object":"model","created":1783669626,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.6-sol@swedencentral","object":"model","created":1783669635,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-sol@swedencentral","object":"model","created":1783669415,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.1@francecentral","object":"model","created":1764178142,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1@swedencentral","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/openai-responses/gpt-4.1","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/gpt-5-mini@swedencentral","object":"model","created":1754524800,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5-nano@francecentral","object":"model","created":1754524800,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5-mini@francecentral","object":"model","created":1754524800,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-5.6-sol@eastus2","object":"model","created":1783669623,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5-nano@swedencentral","object":"model","created":1754524800,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-nano@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"azure/openai-responses/gpt-5.4-pro@eastus2","object":"model","created":1765472400,"owned_by":"system","input_price":0.00003,"cached_price":0.00003,"output_price":0.00018,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.4-mini","object":"model","created":1773705600,"owned_by":"system","input_price":7.5e-7,"cached_price":7.5e-8,"output_price":0.0000045,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.6-sol@eastus2","object":"model","created":1783669626,"owned_by":"system","input_price":0.000005,"cached_price":5e-7,"output_price":0.00003,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5@francecentral","object":"model","created":1754524800,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-4.1-nano@swedencentral","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5-nano@eastus2","object":"model","created":1754524800,"owned_by":"system","input_price":5e-8,"cached_price":5e-9,"output_price":4e-7,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.2@eastus2","object":"model","created":1769448542,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1-nano@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-nano","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"global","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"azure/gpt-5.4@eastus2","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT 5.4 is OpenAI's frontier model designed for complex professional workloads, with strong reasoning, high reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.4","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT 5.4 is OpenAI's frontier model designed for complex professional workloads, with strong reasoning, high reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1@francecentral","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/openai-responses/gpt-4.1@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":0.000002,"cached_price":5e-7,"output_price":0.000008,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5.4@francecentral","object":"model","created":1772668800,"owned_by":"system","input_price":0.0000025,"cached_price":2.5e-7,"output_price":0.000015,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT 5.4 is OpenAI's frontier model designed for complex professional workloads, with strong reasoning, high reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large scale reasoning, coding, and multimodal workflows within a single system.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.3-codex@eastus2","object":"model","created":1771891200,"owned_by":"system","input_price":0.00000175,"cached_price":1.75e-7,"output_price":0.000014,"max_output_tokens":128000,"context_window":400000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-5-mini@eastus2","object":"model","created":1754524800,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1-nano@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-mini@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1-mini@westus3","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/gpt-4.1-nano@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"us"},{"api":"chat","id":"azure/openai-responses/gpt-4.1-nano@eastus2","object":"model","created":1744655100,"owned_by":"system","input_price":1e-7,"cached_price":2.5e-8,"output_price":4e-7,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":true,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","privacy_comments":"N/A","geolocation":"us","retires_at":"2026-10-23T00:00:00Z"},{"api":"chat","id":"azure/gpt-5.1","object":"model","created":1764178142,"owned_by":"system","input_price":0.00000125,"cached_price":1.25e-7,"output_price":0.00001,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"azure/gpt-4.1-mini@uksouth","object":"model","created":1744655100,"owned_by":"system","input_price":4e-7,"cached_price":1e-7,"output_price":0.0000016,"max_output_tokens":32768,"context_window":1047576,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5.6-luna@swedencentral","object":"model","created":1783669635,"owned_by":"system","input_price":0.000001,"cached_price":1e-7,"output_price":0.000006,"max_output_tokens":128000,"context_window":1050000,"supports_caching":true,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"azure/gpt-5-mini@uksouth","object":"model","created":1754524800,"owned_by":"system","input_price":2.5e-7,"cached_price":2.5e-8,"output_price":0.000002,"max_output_tokens":100000,"context_window":200000,"supports_caching":true,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/google/gemma-3-27b-it","object":"model","created":1781598877,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":8192,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"Google mid-size model optimized for high-quality instruction following, coding, and multilingual performance.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/deepseek-ai/DeepSeek-V3.2","object":"model","created":1772282644,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":4.5e-7,"max_output_tokens":128000,"context_window":164000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.","privacy_comments":"Don't store prompts and responses","geolocation":"global","retires_at":"2026-06-22T00:00:00Z"},{"api":"chat","id":"nebius/meta-llama/Llama-3.3-70B-Instruct","object":"model","created":1715697754,"owned_by":"system","input_price":1.3e-7,"cached_price":1.3e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":false,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.","privacy_comments":"Don't store prompts and responses","geolocation":"eu"},{"api":"chat","id":"nebius/zai-org/glm-5.1","object":"model","created":1779285239,"owned_by":"system","input_price":0.0000014,"cached_price":0.0000014,"output_price":0.0000044,"max_output_tokens":0,"context_window":200000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Zhipu AI flagship multimodal model with strong bilingual Chinese English reasoning, long context understanding, advanced tool use, and agent oriented capabilities.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1781598840,"owned_by":"system","input_price":0.000001,"cached_price":0.000001,"output_price":0.000003,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Nemotron 3 Ultra is a 550B hybrid MoE model from NVIDIA, optimized for the most demanding multi-agent AI and complex reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nebius/nvidia/nemotron-3-super-120b-a12b","object":"model","created":1781598844,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":9e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Nemotron 3 Super is a 120B hybrid MoE model optimized for efficient multi-agent AI and complex reasoning tasks.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nebius/nvidia/nemotron-3-nano-omni","object":"model","created":1779285239,"owned_by":"system","input_price":6e-8,"cached_price":6e-8,"output_price":2.4e-7,"max_output_tokens":0,"context_window":300000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/glm-5.2","object":"model","created":1781645757,"owned_by":"system","input_price":0.0000014,"cached_price":0,"output_price":0.0000044,"max_output_tokens":131072,"context_window":1000000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":false,"supports_output_json_schema":false,"description":"GLM-5.2 is Zhipu AI's latest flagship model with strong bilingual (Chinese-English) reasoning, long-context understanding, advanced tool use, and agent-oriented capabilities. The latest model in the GLM series, designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks. Hosted on Nebius at fp8 quantization.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/moonshotai/kimi-k2.5","object":"model","created":1771249200,"owned_by":"system","input_price":5e-7,"cached_price":5e-7,"output_price":0.0000025,"max_output_tokens":128000,"context_window":256000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base","privacy_comments":"N/A","geolocation":"eu","retires_at":"2026-06-22T00:00:00Z"},{"api":"chat","id":"nebius/qwen/qwen3-235b-a22b-instruct-2507","object":"model","created":1781598853,"owned_by":"system","input_price":2e-7,"cached_price":2e-7,"output_price":6e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Balanced Qwen3 flagship tuned for strong general reasoning, chat quality, and tool use.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/openai/gpt-oss-120b","object":"model","created":1772444580,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":6e-7,"max_output_tokens":128000,"context_window":131000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Open-weight agentic model with configurable reasoning, full CoT visibility, strong tool use, and fine-tuning support.","privacy_comments":"Don't store prompts and responses","geolocation":"eu"},{"api":"chat","id":"nebius/moonshotai/kimi-k2.6","object":"model","created":1781598039,"owned_by":"system","input_price":9.5e-7,"cached_price":9.5e-7,"output_price":0.000004,"max_output_tokens":128000,"context_window":256000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Kimi K2.6 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nebius/deepseek-ai/deepseek-v4-pro","object":"model","created":1781598821,"owned_by":"system","input_price":0.00000175,"cached_price":0.00000175,"output_price":0.0000035,"max_output_tokens":128000,"context_window":164000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"DeepSeek-V4 is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.","privacy_comments":"N/A","geolocation":"uk"},{"api":"chat","id":"nebius/qwen/qwen3.5-397b-a17b","object":"model","created":1781598850,"owned_by":"system","input_price":6e-7,"cached_price":6e-7,"output_price":0.0000036,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":true,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Multimodal model featuring a Hybrid Mixture-of-Experts architecture, designed for state-of-the-art performance across chat, retrieval-augmented generation, vision-language understanding, video understanding, and agentic workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nebius/nousresearch/hermes-4-70b","object":"model","created":1781598859,"owned_by":"system","input_price":1.3e-7,"cached_price":1.3e-7,"output_price":4e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Compact version of Hermes-4 delivering high-quality reasoning and coding with lower inference cost.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/nousresearch/hermes-4-405b","object":"model","created":1779285239,"owned_by":"system","input_price":0.000001,"cached_price":0.000001,"output_price":0.000003,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Hybrid reasoning model trained on verified CoT traces for strong math, coding, and step by step reliability.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/minimaxi/minimax-m2.5","object":"model","created":1781598847,"owned_by":"system","input_price":3e-7,"cached_price":3e-7,"output_price":0.0000012,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Open-source agentic coding model built for polyglot development and precision refactoring, using interleaved-thinking tool calls to reliably execute long, multi-step coding and office workflows.","privacy_comments":"N/A","geolocation":"global"},{"api":"chat","id":"nebius/qwen/qwen3-30b-a3b-instruct-2507","object":"model","created":1781598856,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Versatile 30B instruct model optimized for high-quality chat, reasoning, and coding.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/qwen/qwen3-next-80b-a3b-thinking","object":"model","created":1781598864,"owned_by":"system","input_price":1.5e-7,"cached_price":1.5e-7,"output_price":0.0000012,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Qwen thinking-optimized 80B model designed for sustained multi-step reasoning, structured deliberation, and high-precision problem-solving across math, code, and complex planning tasks.","privacy_comments":"N/A","geolocation":"eu"},{"api":"chat","id":"nebius/qwen/qwen3-32b","object":"model","created":1781598867,"owned_by":"system","input_price":1e-7,"cached_price":1e-7,"output_price":3e-7,"max_output_tokens":0,"context_window":128000,"supports_caching":false,"supports_vision":false,"supports_computer_use":false,"supports_reasoning":true,"supports_image_generation":false,"supports_tool_calling":true,"supports_role_developer":false,"supports_web_search":false,"supports_output_json_object":true,"supports_output_json_schema":true,"description":"Generalist model offering strong multilingual reasoning, coding, and long-context performance at mid scale.","privacy_comments":"N/A","geolocation":"eu"}]}