{"data":[{"id":"openrouter:043a453c-8450-4da8-82c1-cf6cc19cba9e","slug":"anthropic/anthropic-claude-opus-5-5-20260921--endpoint-043a453c-8450-4da8-82c1-cf6cc19cba9e","provider":"Anthropic","name":"Anthropic: Claude Opus 5.5","shortName":"Claude Opus 5.5","author":"Anthropic","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.\n\nThe model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-opus-5.5-20260921","endpointId":"043a453c-8450-4da8-82c1-cf6cc19cba9e","promptPrice":0.000004,"completionPrice":0.00002,"modalityScore":3,"throughput":79,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:41d2915a-92e6-4993-b537-210b4e10cba8","slug":"anthropic/anthropic-claude-4-5-haiku-20251001--endpoint-41d2915a-92e6-4993-b537-210b4e10cba8","provider":"Anthropic","name":"Anthropic: Claude Haiku 4.5","shortName":"Claude Haiku 4.5","author":"Anthropic","description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","modelVersionGroupId":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","contextLength":200000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.5-haiku-20251001","endpointId":"41d2915a-92e6-4993-b537-210b4e10cba8","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":78,"maxCompletionTokens":64000,"supportedParameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:b5642c35-75b9-488f-9480-5010d4f2798f","slug":"anthropic/anthropic-claude-haiku-5-5-20261007--endpoint-b5642c35-75b9-488f-9480-5010d4f2798f","provider":"Anthropic","name":"Anthropic: Claude Haiku 5.5","shortName":"Claude Haiku 5.5","author":"Anthropic","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.\n\nIt is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.","modelVersionGroupId":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-haiku-5.5-20261007","endpointId":"b5642c35-75b9-488f-9480-5010d4f2798f","promptPrice":1e-7,"completionPrice":5e-7,"modalityScore":3,"throughput":131,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:72afe8d6-08ba-4171-a15f-fab2259daf02","slug":"anthropic/anthropic-claude-fable-5-1-20260831--endpoint-72afe8d6-08ba-4171-a15f-fab2259daf02","provider":"Anthropic","name":"Anthropic: Claude Fable 5.1","shortName":"Claude Fable 5.1","author":"Anthropic","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","modelVersionGroupId":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-fable-5.1-20260831","endpointId":"72afe8d6-08ba-4171-a15f-fab2259daf02","promptPrice":0.00001,"completionPrice":0.00005,"modalityScore":3,"throughput":66,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:510863e2-e533-4f26-83c1-2b6bb831eb13","slug":"anthropic/anthropic-claude-opus-5-20260723--endpoint-510863e2-e533-4f26-83c1-2b6bb831eb13","provider":"Anthropic","name":"Anthropic: Claude Opus 5","shortName":"Claude Opus 5","author":"Anthropic","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-opus-5-20260723","endpointId":"510863e2-e533-4f26-83c1-2b6bb831eb13","promptPrice":0.00001,"completionPrice":0.00005,"modalityScore":3,"throughput":132,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:be883404-eb42-4b2d-b6e4-c7daa3aa8d62","slug":"anthropic/anthropic-claude-4-5-opus-20251124--endpoint-be883404-eb42-4b2d-b6e4-c7daa3aa8d62","provider":"Anthropic","name":"Anthropic: Claude Opus 4.5","shortName":"Claude Opus 4.5","author":"Anthropic","description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.5-opus-20251124","endpointId":"be883404-eb42-4b2d-b6e4-c7daa3aa8d62","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":43,"maxCompletionTokens":64000,"supportedParameters":["reasoning","include_reasoning","max_tokens","temperature","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:adbe7cef-baaa-428c-8b8d-59d93e17cb47","slug":"anthropic/anthropic-claude-5-fable-20260609--endpoint-adbe7cef-baaa-428c-8b8d-59d93e17cb47","provider":"Anthropic","name":"Anthropic: Claude Fable 5","shortName":"Claude Fable 5","author":"Anthropic","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","modelVersionGroupId":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-5-fable-20260609","endpointId":"adbe7cef-baaa-428c-8b8d-59d93e17cb47","promptPrice":0.00001,"completionPrice":0.00005,"modalityScore":3,"throughput":51,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:6d408764-7dd7-4626-bb87-a6cc1589bc86","slug":"anthropic/anthropic-claude-4-6-sonnet-20260217--endpoint-6d408764-7dd7-4626-bb87-a6cc1589bc86","provider":"Anthropic","name":"Anthropic: Claude Sonnet 4.6","shortName":"Claude Sonnet 4.6","author":"Anthropic","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.","modelVersionGroupId":"abf62d9f-0b98-401f-a916-b5bd3c214712","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.6-sonnet-20260217","endpointId":"6d408764-7dd7-4626-bb87-a6cc1589bc86","promptPrice":0.000003,"completionPrice":0.000015,"modalityScore":3,"throughput":37,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:34c7c6ba-4cb1-4aa1-a940-bda19245da16","slug":"anthropic/anthropic-claude-4-8-opus-20260528--endpoint-34c7c6ba-4cb1-4aa1-a940-bda19245da16","provider":"Anthropic","name":"Anthropic: Claude Opus 4.8","shortName":"Claude Opus 4.8","author":"Anthropic","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.8-opus-20260528","endpointId":"34c7c6ba-4cb1-4aa1-a940-bda19245da16","promptPrice":0.00001,"completionPrice":0.00005,"modalityScore":3,"throughput":168,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:f2e829ec-4a2c-45c4-9657-fd5998271267","slug":"anthropic/anthropic-claude-4-5-sonnet-20250929--endpoint-f2e829ec-4a2c-45c4-9657-fd5998271267","provider":"Anthropic","name":"Anthropic: Claude Sonnet 4.5","shortName":"Claude Sonnet 4.5","author":"Anthropic","description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","modelVersionGroupId":null,"contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.5-sonnet-20250929","endpointId":"f2e829ec-4a2c-45c4-9657-fd5998271267","promptPrice":0.000003,"completionPrice":0.000015,"modalityScore":3,"throughput":42,"maxCompletionTokens":64000,"supportedParameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:e63fd240-af20-45b8-a90b-dfcc32170f1f","slug":"anthropic/anthropic-claude-opus-5-5-20260921--endpoint-e63fd240-af20-45b8-a90b-dfcc32170f1f","provider":"Anthropic","name":"Anthropic: Claude Opus 5.5","shortName":"Claude Opus 5.5","author":"Anthropic","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.\n\nThe model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-opus-5.5-20260921","endpointId":"e63fd240-af20-45b8-a90b-dfcc32170f1f","promptPrice":0.000008,"completionPrice":0.00004,"modalityScore":3,"throughput":143,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:8120faed-3f9c-4758-931e-4154e9b5a503","slug":"anthropic/anthropic-claude-sonnet-5-5-20260928--endpoint-8120faed-3f9c-4758-931e-4154e9b5a503","provider":"Anthropic","name":"Anthropic: Claude Sonnet 5.5","shortName":"Claude Sonnet 5.5","author":"Anthropic","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.\n\nThinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.","modelVersionGroupId":"abf62d9f-0b98-401f-a916-b5bd3c214712","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-sonnet-5.5-20260928","endpointId":"8120faed-3f9c-4758-931e-4154e9b5a503","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":105,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:dfc0e5bd-d703-4fe2-a7bb-655eb95d5441","slug":"anthropic/anthropic-claude-4-8-opus-20260528--endpoint-dfc0e5bd-d703-4fe2-a7bb-655eb95d5441","provider":"Anthropic","name":"Anthropic: Claude Opus 4.8","shortName":"Claude Opus 4.8","author":"Anthropic","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.8-opus-20260528","endpointId":"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":49,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:c926c048-563e-44b0-8434-95965bee924c","slug":"anthropic/anthropic-claude-4-6-opus-20260205--endpoint-c926c048-563e-44b0-8434-95965bee924c","provider":"Anthropic","name":"Anthropic: Claude Opus 4.6","shortName":"Claude Opus 4.6","author":"Anthropic","description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)\n","modelVersionGroupId":null,"contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.6-opus-20260205","endpointId":"c926c048-563e-44b0-8434-95965bee924c","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":34,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:a6a218f6-0bca-440c-98b5-66bccd2f9480","slug":"anthropic/anthropic-claude-opus-5-20260723--endpoint-a6a218f6-0bca-440c-98b5-66bccd2f9480","provider":"Anthropic","name":"Anthropic: Claude Opus 5","shortName":"Claude Opus 5","author":"Anthropic","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-opus-5-20260723","endpointId":"a6a218f6-0bca-440c-98b5-66bccd2f9480","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":61,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:0a2a206f-95f6-4173-9475-fe65a9a36171","slug":"anthropic/anthropic-claude-sonnet-5-20260630--endpoint-0a2a206f-95f6-4173-9475-fe65a9a36171","provider":"Anthropic","name":"Anthropic: Claude Sonnet 5","shortName":"Claude Sonnet 5","author":"Anthropic","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","modelVersionGroupId":"abf62d9f-0b98-401f-a916-b5bd3c214712","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-sonnet-5-20260630","endpointId":"0a2a206f-95f6-4173-9475-fe65a9a36171","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":75,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:71784905-0c14-4c62-851a-c998ae9a222c","slug":"anthropic/anthropic-claude-4-7-opus-20260416--endpoint-71784905-0c14-4c62-851a-c998ae9a222c","provider":"Anthropic","name":"Anthropic: Claude Opus 4.7","shortName":"Claude Opus 4.7","author":"Anthropic","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.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/evaluate-and-optimize/model-migrations/claude-4-7)\n","modelVersionGroupId":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","contextLength":1000000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.7-opus-20260416","endpointId":"71784905-0c14-4c62-851a-c998ae9a222c","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":48,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:bc6f8bb1-798f-4a72-99ec-bc3009f8122e","slug":"openai/openai-gpt-6-luna-20260922--endpoint-bc6f8bb1-798f-4a72-99ec-bc3009f8122e","provider":"OpenAI","name":"OpenAI: GPT-6 Luna","shortName":"GPT-6 Luna","author":"OpenAI","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.","modelVersionGroupId":"a064a4e3-1bc0-4b48-9d3d-90ad033767af","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6-luna-20260922","endpointId":"bc6f8bb1-798f-4a72-99ec-bc3009f8122e","promptPrice":2e-7,"completionPrice":0.000001,"modalityScore":3,"throughput":72,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:697e2929-5f65-44e5-a35f-9e65fa63555a","slug":"openai/openai-gpt-6-1-sol-20260929--endpoint-697e2929-5f65-44e5-a35f-9e65fa63555a","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol","shortName":"GPT-6.1 Sol","author":"OpenAI","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-20260929","endpointId":"697e2929-5f65-44e5-a35f-9e65fa63555a","promptPrice":0.000004,"completionPrice":0.00002,"modalityScore":3,"throughput":66,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:b6286562-1665-4a4e-8ce1-ae5a77dc078f","slug":"openai/openai-gpt-6-luna-pro-20260922--endpoint-b6286562-1665-4a4e-8ce1-ae5a77dc078f","provider":"OpenAI","name":"OpenAI: GPT-6 Luna Pro","shortName":"GPT-6 Luna Pro","author":"OpenAI","description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6-luna-pro-20260922","endpointId":"b6286562-1665-4a4e-8ce1-ae5a77dc078f","promptPrice":1e-7,"completionPrice":5e-7,"modalityScore":3,"throughput":101,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:b8222376-66ee-4b89-a7c9-e627ba35db79","slug":"openai/openai-o3-pro-2025-06-10--endpoint-b8222376-66ee-4b89-a7c9-e627ba35db79","provider":"OpenAI","name":"OpenAI: o3 Pro","shortName":"o3 Pro","author":"OpenAI","description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Text","File","Image"],"outputModalities":["Text"],"permaslug":"openai/o3-pro-2025-06-10","endpointId":"b8222376-66ee-4b89-a7c9-e627ba35db79","promptPrice":0.00002,"completionPrice":0.00008,"modalityScore":3,"throughput":26,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:be0ed145-8bfc-4aec-a62d-685ed334fe17","slug":"openai/openai-gpt-5-image--endpoint-be0ed145-8bfc-4aec-a62d-685ed334fe17","provider":"OpenAI","name":"OpenAI: GPT-5 Image","shortName":"GPT-5 Image","author":"OpenAI","description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Image","Text","File"],"outputModalities":["Image","Text"],"permaslug":"openai/gpt-5-image","endpointId":"be0ed145-8bfc-4aec-a62d-685ed334fe17","promptPrice":0.00001,"completionPrice":0.00001,"modalityScore":3,"throughput":87,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","verbosity","logprobs","temperature","top_logprobs","top_p"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:ed722d80-aa3d-4e80-b3f1-d787705bddf8","slug":"openai/openai-gpt-5-6-terra-pro-20260709--endpoint-ed722d80-aa3d-4e80-b3f1-d787705bddf8","provider":"OpenAI","name":"OpenAI: GPT-5.6 Terra Pro","shortName":"GPT-5.6 Terra Pro","author":"OpenAI","description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.6-terra-pro-20260709","endpointId":"ed722d80-aa3d-4e80-b3f1-d787705bddf8","promptPrice":0.000004,"completionPrice":0.000024,"modalityScore":3,"throughput":244,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:eebea444-34a5-4642-a766-cb319471d33a","slug":"openai/openai-gpt-5-6-luna-20260709--endpoint-eebea444-34a5-4642-a766-cb319471d33a","provider":"OpenAI","name":"OpenAI: GPT-5.6 Luna","shortName":"GPT-5.6 Luna","author":"OpenAI","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.","modelVersionGroupId":"a064a4e3-1bc0-4b48-9d3d-90ad033767af","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.6-luna-20260709","endpointId":"eebea444-34a5-4642-a766-cb319471d33a","promptPrice":2e-7,"completionPrice":0.0000012,"modalityScore":3,"throughput":63,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:2765608f-de81-4d51-8590-25448b5873ff","slug":"openai/openai-gpt-6-1-sol-20260929--endpoint-2765608f-de81-4d51-8590-25448b5873ff","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol","shortName":"GPT-6.1 Sol","author":"OpenAI","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-20260929","endpointId":"2765608f-de81-4d51-8590-25448b5873ff","promptPrice":0.000012,"completionPrice":0.00006,"modalityScore":3,"throughput":32,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:89564020-af23-49f4-b570-2d9d47e7e40f","slug":"openai/openai-gpt-5-6-luna-pro-20260709--endpoint-89564020-af23-49f4-b570-2d9d47e7e40f","provider":"OpenAI","name":"OpenAI: GPT-5.6 Luna Pro","shortName":"GPT-5.6 Luna Pro","author":"OpenAI","description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.6-luna-pro-20260709","endpointId":"89564020-af23-49f4-b570-2d9d47e7e40f","promptPrice":1e-7,"completionPrice":6e-7,"modalityScore":3,"throughput":106,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:5dbc1496-5b63-4a4e-94ea-e8d1dc61fcf4","slug":"openai/openai-gpt-6-1-sol-20260929--endpoint-5dbc1496-5b63-4a4e-94ea-e8d1dc61fcf4","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol","shortName":"GPT-6.1 Sol","author":"OpenAI","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-20260929","endpointId":"5dbc1496-5b63-4a4e-94ea-e8d1dc61fcf4","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":48,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:33cb8d87-3805-419b-a340-9a439614732a","slug":"openai/openai-gpt-6-luna-pro-20260922--endpoint-33cb8d87-3805-419b-a340-9a439614732a","provider":"OpenAI","name":"OpenAI: GPT-6 Luna Pro","shortName":"GPT-6 Luna Pro","author":"OpenAI","description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6-luna-pro-20260922","endpointId":"33cb8d87-3805-419b-a340-9a439614732a","promptPrice":5e-8,"completionPrice":2.5e-7,"modalityScore":3,"throughput":57,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:7c09094a-64ec-4d53-bd69-c165ac31c465","slug":"openai/openai-gpt-5-image-mini--endpoint-7c09094a-64ec-4d53-bd69-c165ac31c465","provider":"OpenAI","name":"OpenAI: GPT-5 Image Mini","shortName":"GPT-5 Image Mini","author":"OpenAI","description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["File","Image","Text"],"outputModalities":["Image","Text"],"permaslug":"openai/gpt-5-image-mini","endpointId":"7c09094a-64ec-4d53-bd69-c165ac31c465","promptPrice":0.0000025,"completionPrice":0.000002,"modalityScore":3,"throughput":124,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","verbosity","logprobs","temperature","top_logprobs","top_p"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:7c2f859a-7890-4e8e-b1de-1cd1c0a800b4","slug":"openai/openai-gpt-5-2025-08-07--endpoint-7c2f859a-7890-4e8e-b1de-1cd1c0a800b4","provider":"OpenAI","name":"OpenAI: GPT-5","shortName":"GPT-5","author":"OpenAI","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.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5-2025-08-07","endpointId":"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4","promptPrice":0.00000125,"completionPrice":0.00001,"modalityScore":3,"throughput":77,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:48e281c4-8271-4725-a5e8-bd2a2f6ffb23","slug":"openai/openai-gpt-6-1-sol-pro-20260929--endpoint-48e281c4-8271-4725-a5e8-bd2a2f6ffb23","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol Pro","shortName":"GPT-6.1 Sol Pro","author":"OpenAI","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-pro-20260929","endpointId":"48e281c4-8271-4725-a5e8-bd2a2f6ffb23","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":74,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:a775a298-1154-44d8-9db7-c2b9e75fba9a","slug":"openai/openai-gpt-5-6-terra-pro-20260709--endpoint-a775a298-1154-44d8-9db7-c2b9e75fba9a","provider":"OpenAI","name":"OpenAI: GPT-5.6 Terra Pro","shortName":"GPT-5.6 Terra Pro","author":"OpenAI","description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.6-terra-pro-20260709","endpointId":"a775a298-1154-44d8-9db7-c2b9e75fba9a","promptPrice":0.000002,"completionPrice":0.000012,"modalityScore":3,"throughput":102,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:a4506ec7-5f3a-4fc4-9bea-e2c4f7f95216","slug":"openai/openai-gpt-6-1-sol-pro-20260929--endpoint-a4506ec7-5f3a-4fc4-9bea-e2c4f7f95216","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol Pro","shortName":"GPT-6.1 Sol Pro","author":"OpenAI","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-pro-20260929","endpointId":"a4506ec7-5f3a-4fc4-9bea-e2c4f7f95216","promptPrice":0.000004,"completionPrice":0.00002,"modalityScore":3,"throughput":23,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:2d2ad10f-098e-4bbf-aa95-11f705b2b9a2","slug":"openai/openai-gpt-6-1-terra-20261026--endpoint-2d2ad10f-098e-4bbf-aa95-11f705b2b9a2","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra","shortName":"GPT-6.1 Terra","author":"OpenAI","description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-20261026","endpointId":"2d2ad10f-098e-4bbf-aa95-11f705b2b9a2","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":56,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:67ae46eb-2f8e-477b-8381-0eee78aaba0e","slug":"openai/openai-gpt-6-1-terra-pro-20261026--endpoint-67ae46eb-2f8e-477b-8381-0eee78aaba0e","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra Pro","shortName":"GPT-6.1 Terra Pro","author":"OpenAI","description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-pro-20261026","endpointId":"67ae46eb-2f8e-477b-8381-0eee78aaba0e","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":90,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:cd85edae-cfd2-40fd-b4a9-fced7d0526bf","slug":"openai/openai-gpt-6-luna-decisions-20261006--endpoint-cd85edae-cfd2-40fd-b4a9-fced7d0526bf","provider":"OpenAI","name":"OpenAI: GPT-6 Luna Decisions","shortName":"GPT-6 Luna Decisions","author":"OpenAI","description":"GPT-6 Luna Decisions is [GPT-6 Luna](/openai/gpt-6-luna) served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as `state` (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (`noul`), a probability for every option plus the most likely one (`choice`), or a probability for every level of an ordered rubric plus the expected score (`score`).\n\nIt is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["Text","Image"],"outputModalities":["Decisions"],"permaslug":"openai/gpt-6-luna-decisions-20261006","endpointId":"cd85edae-cfd2-40fd-b4a9-fced7d0526bf","promptPrice":1e-7,"completionPrice":0,"modalityScore":3,"throughput":null,"maxCompletionTokens":945000,"supportedParameters":[],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:e666fbdb-19ee-4927-be55-8e56102a014f","slug":"openai/openai-gpt-6-1-sol-pro-20260929--endpoint-e666fbdb-19ee-4927-be55-8e56102a014f","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol Pro","shortName":"GPT-6.1 Sol Pro","author":"OpenAI","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-pro-20260929","endpointId":"e666fbdb-19ee-4927-be55-8e56102a014f","promptPrice":0.000012,"completionPrice":0.00006,"modalityScore":3,"throughput":135,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:50329d77-04e1-4979-a184-c33030289476","slug":"openai/openai-gpt-5-nano-2025-08-07--endpoint-50329d77-04e1-4979-a184-c33030289476","provider":"OpenAI","name":"OpenAI: GPT-5 Nano","shortName":"GPT-5 Nano","author":"OpenAI","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5-nano-2025-08-07","endpointId":"50329d77-04e1-4979-a184-c33030289476","promptPrice":5e-8,"completionPrice":4e-7,"modalityScore":3,"throughput":81,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15","slug":"openai/openai-gpt-4o-mini-2024-07-18--endpoint-ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15","provider":"OpenAI","name":"OpenAI: GPT-4o-mini (2024-07-18)","shortName":"GPT-4o-mini (2024-07-18)","author":"OpenAI","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","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-4o-mini-2024-07-18","endpointId":"ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15","promptPrice":1.5e-7,"completionPrice":6e-7,"modalityScore":3,"throughput":46,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:a954b9eb-53b5-43b3-addf-d47d08f0453a","slug":"openai/openai-gpt-6-1-terra-pro-20261026--endpoint-a954b9eb-53b5-43b3-addf-d47d08f0453a","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra Pro","shortName":"GPT-6.1 Terra Pro","author":"OpenAI","description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-pro-20261026","endpointId":"a954b9eb-53b5-43b3-addf-d47d08f0453a","promptPrice":5e-7,"completionPrice":0.0000025,"modalityScore":3,"throughput":101,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:ff94b1f1-db76-42c5-a21e-06083c3cc7d0","slug":"openai/openai-gpt-5-6-luna-20260709--endpoint-ff94b1f1-db76-42c5-a21e-06083c3cc7d0","provider":"OpenAI","name":"OpenAI: GPT-5.6 Luna","shortName":"GPT-5.6 Luna","author":"OpenAI","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.","modelVersionGroupId":"a064a4e3-1bc0-4b48-9d3d-90ad033767af","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.6-luna-20260709","endpointId":"ff94b1f1-db76-42c5-a21e-06083c3cc7d0","promptPrice":1e-7,"completionPrice":6e-7,"modalityScore":3,"throughput":81,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:77e40332-6f2a-4c48-bc14-e44596b30ce2","slug":"openai/openai-gpt-4o-mini--endpoint-77e40332-6f2a-4c48-bc14-e44596b30ce2","provider":"OpenAI","name":"OpenAI: GPT-4o-mini","shortName":"GPT-4o-mini","author":"OpenAI","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","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-4o-mini","endpointId":"77e40332-6f2a-4c48-bc14-e44596b30ce2","promptPrice":1.5e-7,"completionPrice":6e-7,"modalityScore":3,"throughput":46,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:86e3e664-d291-415d-a769-8e08b96a79e9","slug":"openai/openai-gpt-5-pro-2025-10-06--endpoint-86e3e664-d291-415d-a769-8e08b96a79e9","provider":"OpenAI","name":"OpenAI: GPT-5 Pro","shortName":"GPT-5 Pro","author":"OpenAI","description":"GPT-5 Pro 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.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5-pro-2025-10-06","endpointId":"86e3e664-d291-415d-a769-8e08b96a79e9","promptPrice":0.000015,"completionPrice":0.00012,"modalityScore":3,"throughput":5,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:784594bd-7a8c-4be1-ba47-e2af1f41dcb5","slug":"openai/openai-gpt-5-mini-2025-08-07--endpoint-784594bd-7a8c-4be1-ba47-e2af1f41dcb5","provider":"OpenAI","name":"OpenAI: GPT-5 Mini","shortName":"GPT-5 Mini","author":"OpenAI","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5-mini-2025-08-07","endpointId":"784594bd-7a8c-4be1-ba47-e2af1f41dcb5","promptPrice":1.25e-7,"completionPrice":0.000001,"modalityScore":3,"throughput":67,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:3f4c825d-81d1-4018-bc3d-676cce1d7c40","slug":"openai/openai-gpt-6-1-terra-20261026--endpoint-3f4c825d-81d1-4018-bc3d-676cce1d7c40","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra","shortName":"GPT-6.1 Terra","author":"OpenAI","description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-20261026","endpointId":"3f4c825d-81d1-4018-bc3d-676cce1d7c40","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":59,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:d5b3e368-8a97-4e85-899d-52abab5bf318","slug":"openai/openai-gpt-6-1-terra-pro-20261026--endpoint-d5b3e368-8a97-4e85-899d-52abab5bf318","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra Pro","shortName":"GPT-6.1 Terra Pro","author":"OpenAI","description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-pro-20261026","endpointId":"d5b3e368-8a97-4e85-899d-52abab5bf318","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":171.5,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:9230ef3b-f055-424f-9645-68cebd08c1af","slug":"openai/openai-gpt-6-1-terra-20261026--endpoint-9230ef3b-f055-424f-9645-68cebd08c1af","provider":"OpenAI","name":"OpenAI: GPT-6.1 Terra","shortName":"GPT-6.1 Terra","author":"OpenAI","description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-terra-20261026","endpointId":"9230ef3b-f055-424f-9645-68cebd08c1af","promptPrice":5e-7,"completionPrice":0.0000025,"modalityScore":3,"throughput":44,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:72224607-a759-452e-9fb6-1c44c122b6d3","slug":"openai/openai-gpt-5-nano-2025-08-07--endpoint-72224607-a759-452e-9fb6-1c44c122b6d3","provider":"OpenAI","name":"OpenAI: GPT-5 Nano","shortName":"GPT-5 Nano","author":"OpenAI","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5-nano-2025-08-07","endpointId":"72224607-a759-452e-9fb6-1c44c122b6d3","promptPrice":2.5e-8,"completionPrice":2e-7,"modalityScore":3,"throughput":105,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:9c3f44c5-6c7d-457c-8ad0-c6829dd3f016","slug":"openai/openai-gpt-6-1-sol-pro-20260929--endpoint-9c3f44c5-6c7d-457c-8ad0-c6829dd3f016","provider":"OpenAI","name":"OpenAI: GPT-6.1 Sol Pro","shortName":"GPT-6.1 Sol Pro","author":"OpenAI","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\n**Cost note:** pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol) instead.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","modelVersionGroupId":null,"contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-6.1-sol-pro-20260929","endpointId":"9c3f44c5-6c7d-457c-8ad0-c6829dd3f016","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":68,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"},{"id":"openrouter:7823da09-0b84-4e58-a02f-c727190d10bf","slug":"openai/openai-gpt-5-1-20251113--endpoint-7823da09-0b84-4e58-a02f-c727190d10bf","provider":"OpenAI","name":"OpenAI: GPT-5.1","shortName":"GPT-5.1","author":"OpenAI","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","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.1-20251113","endpointId":"7823da09-0b84-4e58-a02f-c727190d10bf","promptPrice":0.0000025,"completionPrice":0.00002,"modalityScore":3,"throughput":155,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity"],"scrapedAt":"2026-11-07T07:00:09.507Z"}],"meta":{"totalRowCount":1661,"filterRowCount":1661,"facets":{"provider":{"rows":[{"value":"Anthropic","total":17},{"value":"OpenAI","total":112},{"value":"Google AI Studio","total":57},{"value":"DeepSeek","total":2},{"value":"MoonshotAI","total":6},{"value":"Perplexity","total":9},{"value":"MiniMax","total":7},{"value":"Mistral","total":56},{"value":"Cohere","total":18},{"value":"Amazon Bedrock","total":75},{"value":"Xiaomi","total":3},{"value":"Groq","total":8},{"value":"Together","total":21},{"value":"Fireworks","total":19},{"value":"Cerebras","total":2},{"value":"SambaNova","total":4},{"value":"DeepInfra","total":112},{"value":"Google Vertex","total":94},{"value":"Azure","total":118},{"value":"Cloudflare","total":20},{"value":"Crusoe","total":9},{"value":"Friendli","total":5},{"value":"SiliconFlow","total":42},{"value":"Chutes","total":7},{"value":"Venice","total":37},{"value":"Phala","total":21},{"value":"AtlasCloud","total":30},{"value":"NextBit","total":7},{"value":"Parasail","total":49},{"value":"Inception","total":4},{"value":"Relace","total":12},{"value":"Morph","total":10},{"value":"AionLabs","total":6},{"value":"Mancer","total":10},{"value":"Liquid","total":6},{"value":"GMICloud","total":29},{"value":"Featherless","total":1},{"value":"Ambient","total":2},{"value":"Black Forest Labs","total":9},{"value":"Inceptron","total":6},{"value":"Seed","total":16},{"value":"Sourceful","total":5},{"value":"Stealth","total":1},{"value":"StepFun","total":3},{"value":"StreamLake","total":20},{"value":"Upstage","total":8},{"value":"AkashML","total":8},{"value":"Alibaba Cloud Int.","total":54},{"value":"Ant Digital","total":1},{"value":"AssemblyAI","total":4},{"value":"Baidu Qianfan","total":11},{"value":"Baidu Qianfan (fp4)","total":1},{"value":"Baidu Qianfan (fp8)","total":1},{"value":"Baseten","total":22},{"value":"Baseten (fp32)","total":1},{"value":"Baseten (fp4)","total":2},{"value":"Baseten (fp8)","total":3},{"value":"Claude Platform on AWS","total":12},{"value":"CoreWeave","total":23},{"value":"Darkbloom","total":12},{"value":"Decart","total":3},{"value":"Deepgram","total":3},{"value":"DeepInfra (bf16)","total":1},{"value":"DeepInfra (fp4)","total":1},{"value":"DeepInfra (fp8)","total":4},{"value":"DeepInfra (Turbo)","total":3},{"value":"DekaLLM","total":11},{"value":"DigitalOcean","total":20},{"value":"ElevenLabs","total":11},{"value":"Fireworks Spot","total":3},{"value":"Fish Audio","total":6},{"value":"HeyGen","total":4},{"value":"inference.net","total":22},{"value":"io.net","total":6},{"value":"Ionstream","total":2},{"value":"Krea","total":4},{"value":"Makora","total":10},{"value":"Meta","total":8},{"value":"Mistral (nvfp4)","total":1},{"value":"Modal","total":9},{"value":"ModelRun [by Modular]","total":5},{"value":"Morph Fast","total":1},{"value":"NEAR AI","total":4},{"value":"Nebius Token Factory","total":21},{"value":"Nex AGI","total":2},{"value":"NovitaAI","total":40},{"value":"Open Inference","total":3},{"value":"Pareto Alpha","total":1},{"value":"Particle AI","total":4},{"value":"Perceptron","total":2},{"value":"PrimaLabs","total":3},{"value":"Prime Intellect","total":22},{"value":"Recraft","total":16},{"value":"Reka AI","total":9},{"value":"Respan","total":3},{"value":"Runway","total":2},{"value":"Sail Research","total":15},{"value":"Sakana","total":4},{"value":"SambaNova Turbo","total":1},{"value":"ScaleDown","total":3},{"value":"SpaceXAI","total":36},{"value":"Tencent Cloud","total":7},{"value":"Tenstorrent","total":5},{"value":"TypeSafe","total":2},{"value":"Unbiased","total":2},{"value":"Venice (fp8)","total":1},{"value":"Voyage AI by MongoDB","total":9},{"value":"Wafer","total":21},{"value":"Z.ai","total":15}],"total":1661},"author":{"rows":[{"value":"OpenAI","total":256},{"value":"Anthropic","total":118},{"value":"Google","total":154},{"value":"Meta","total":16},{"value":"DeepSeek","total":192},{"value":"Mistral","total":62},{"value":"Cohere","total":12},{"value":"Perplexity","total":10},{"value":"Microsoft","total":13},{"value":"Qwen","total":148},{"value":"MoonshotAI","total":89},{"value":"Amazon","total":12},{"value":"Alibaba","total":6},{"value":"Tencent","total":19},{"value":"ByteDance","total":17},{"value":"MiniMax","total":41},{"value":"Meituan","total":1},{"value":"Liquid","total":6},{"value":"Inception","total":4},{"value":"Morph","total":3},{"value":"inclusionAI","total":6},{"value":"Relace","total":2},{"value":"Nous Research","total":1},{"value":"Gryphe","total":2},{"value":"Anthracite","total":1},{"value":"Mancer","total":1},{"value":"Sao10K","total":3},{"value":"Undi","total":1},{"value":"BAAI","total":4},{"value":"Black Forest Labs","total":9},{"value":"IBM","total":2},{"value":"intfloat","total":3},{"value":"Nex AGI","total":2},{"value":"Sentence Transformers","total":5},{"value":"Sourceful","total":5},{"value":"StepFun","total":6},{"value":"thenlper","total":2},{"value":"Upstage","total":8},{"value":"Venice","total":1},{"value":"Writer","total":1},{"value":"Xiaomi","total":18},{"value":"Aion Labs","total":6},{"value":"AssemblyAI","total":4},{"value":"Baseten","total":3},{"value":"canopylabs","total":2},{"value":"Cloudflare","total":9},{"value":"deepgram","total":3},{"value":"Drummer","total":3},{"value":"Elevenlabs","total":11},{"value":"Elorian","total":1},{"value":"Fireworks AI","total":1},{"value":"fish-audio","total":6},{"value":"hexgrad","total":2},{"value":"heygen","total":4},{"value":"Inference Net","total":4},{"value":"Jared Palmer","total":2},{"value":"krea","total":4},{"value":"kwaivgi","total":3},{"value":"Meta Llama","total":27},{"value":"MongoDB","total":9},{"value":"Moondream","total":3},{"value":"Nace.AI","total":3},{"value":"Nvidia","total":30},{"value":"Particle AI","total":1},{"value":"perceptron","total":2},{"value":"PrismML","total":2},{"value":"Recraft","total":16},{"value":"Reflection","total":5},{"value":"rekaai","total":2},{"value":"Respan","total":3},{"value":"ricursiveAI","total":1},{"value":"Runway","total":2},{"value":"sakana","total":4},{"value":"Scaledown","total":3},{"value":"sesame","total":1},{"value":"SpaceXAI","total":38},{"value":"Stealth","total":1},{"value":"The Biological Computing Company","total":1},{"value":"thinkingmachines","total":2},{"value":"Together","total":1},{"value":"TypeSafe","total":2},{"value":"Unbiased","total":2},{"value":"Z.ai","total":170}],"total":1661},"modalities":{"rows":[{"value":"Audio","total":169},{"value":"Decisions","total":38},{"value":"Embeddings","total":46},{"value":"File","total":462},{"value":"Image","total":1132},{"value":"Rerank","total":10},{"value":"Speech","total":43},{"value":"Text","total":3017},{"value":"Transcription","total":42},{"value":"Video","total":433}],"total":1661},"name":{"rows":[{"value":"DeepSeek V4.1 Flash 1017","total":49},{"value":"GLM 5.3","total":47},{"value":"GLM 5.3 Flash","total":42},{"value":"DeepSeek V4.1 Flash","total":38},{"value":"GLM 5.2","total":33},{"value":"Kimi K3","total":30},{"value":"DeepSeek V4 Flash 0731","total":29},{"value":"gpt-oss-120b","total":26},{"value":"DeepSeek V4 Pro 0813","total":25},{"value":"Qwen3.8 27B","total":24},{"value":"Kimi K3.1 Pro","total":24},{"value":"Gemma 4 31B","total":19},{"value":"Kimi K2.6","total":16},{"value":"Gemma 4 26B A4B","total":15},{"value":"DeepSeek V4 Pro 0423","total":14},{"value":"DeepSeek V4 Flash 0423","total":14},{"value":"GLM 5.1","total":13},{"value":"MiniMax M3.1 Flash","total":13},{"value":"MiniMax M3","total":12},{"value":"Qwen3.6 35B A3B","total":11}],"total":1661}}},"prevCursor":null,"nextCursor":50}