{"data":[{"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":37,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":123,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":65,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":47,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":31,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":62,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:41d2915a-92e6-4993-b537-210b4e10cba8","slug":"anthropic/anthropic-claude-haiku-latest--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-haiku-latest","endpointId":"41d2915a-92e6-4993-b537-210b4e10cba8","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":65,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":35.5,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":62,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":46,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":85,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":48,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":32,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:f00142c2-6a93-49ce-9e36-5593b904ce3b","slug":"openai/openai-gpt-5-2-20251211--endpoint-f00142c2-6a93-49ce-9e36-5593b904ce3b","provider":"OpenAI","name":"OpenAI: GPT-5.2","shortName":"GPT-5.2","author":"OpenAI","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.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.2-20251211","endpointId":"f00142c2-6a93-49ce-9e36-5593b904ce3b","promptPrice":0.00000175,"completionPrice":0.000014,"modalityScore":3,"throughput":28,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:ed3f5245-1a21-45b0-b358-1d3a9f43773a","slug":"openai/openai-gpt-image-2-5-flare-20260908--endpoint-ed3f5245-1a21-45b0-b358-1d3a9f43773a","provider":"OpenAI","name":"OpenAI: GPT Image 2.5 Flare","shortName":"GPT Image 2.5 Flare","author":"OpenAI","description":"GPT Image 2.5 Flare is an image generation and editing model from OpenAI, positioned as the speed-oriented tier of the GPT Image 2.5 series. It is suited to high-volume everyday generation, creator content, and rapid prototyping via the dedicated Images API.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image"],"outputModalities":["Image"],"permaslug":"openai/gpt-image-2.5-flare-20260908","endpointId":"ed3f5245-1a21-45b0-b358-1d3a9f43773a","promptPrice":0.000008,"completionPrice":0.000008,"modalityScore":2,"throughput":24.5,"maxCompletionTokens":360000,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:ff94b1f1-db76-42c5-a21e-06083c3cc7d0","slug":"openai/openai-gpt-luna-latest--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-luna-latest","endpointId":"ff94b1f1-db76-42c5-a21e-06083c3cc7d0","promptPrice":1e-7,"completionPrice":6e-7,"modalityScore":3,"throughput":36,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":21,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:eb1a93d0-a295-4afb-86d3-e2d10538c12d","slug":"openai/openai-gpt-3-5-turbo-16k--endpoint-eb1a93d0-a295-4afb-86d3-e2d10538c12d","provider":"OpenAI","name":"OpenAI: GPT-3.5 Turbo 16k","shortName":"GPT-3.5 Turbo 16k","author":"OpenAI","description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.","modelVersionGroupId":null,"contextLength":16385,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-3.5-turbo-16k","endpointId":"eb1a93d0-a295-4afb-86d3-e2d10538c12d","promptPrice":0.000003,"completionPrice":0.000004,"modalityScore":1,"throughput":77,"maxCompletionTokens":4096,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:eebea444-34a5-4642-a766-cb319471d33a","slug":"openai/openai-gpt-luna-latest--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-luna-latest","endpointId":"eebea444-34a5-4642-a766-cb319471d33a","promptPrice":2e-7,"completionPrice":0.0000012,"modalityScore":3,"throughput":61,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:69f070e8-16b8-4eea-be69-49a89c501c18","slug":"openai/openai-gpt-transcribe-20260805--endpoint-69f070e8-16b8-4eea-be69-49a89c501c18","provider":"OpenAI","name":"OpenAI: GPT Transcribe","shortName":"GPT Transcribe","author":"OpenAI","description":"GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language hints for specialized terms and multilingual speech.","modelVersionGroupId":null,"contextLength":null,"inputModalities":["Audio"],"outputModalities":["Transcription"],"permaslug":"openai/gpt-transcribe-20260805","endpointId":"69f070e8-16b8-4eea-be69-49a89c501c18","promptPrice":0.000075,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":0,"supportedParameters":[],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:64614955-f8a2-4d65-bad7-88186222018e","slug":"openai/openai-gpt-astra-latest--endpoint-64614955-f8a2-4d65-bad7-88186222018e","provider":"OpenAI","name":"OpenAI: GPT-6 Astra","shortName":"GPT-6 Astra","author":"OpenAI","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","modelVersionGroupId":"310ee917-8b07-4b12-8c29-a7a37b56cc8a","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-astra-latest","endpointId":"64614955-f8a2-4d65-bad7-88186222018e","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":9,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":102,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:c2928094-b04c-4f41-84b2-2bf508091421","slug":"openai/openai-gpt-astra-latest--endpoint-c2928094-b04c-4f41-84b2-2bf508091421","provider":"OpenAI","name":"OpenAI: GPT-6 Astra","shortName":"GPT-6 Astra","author":"OpenAI","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","modelVersionGroupId":"310ee917-8b07-4b12-8c29-a7a37b56cc8a","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-astra-latest","endpointId":"c2928094-b04c-4f41-84b2-2bf508091421","promptPrice":0.00001,"completionPrice":0.00005,"modalityScore":3,"throughput":29,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:e93c942e-7f8f-410d-8478-21ec37bc6b0d","slug":"openai/openai-o3-mini-2025-01-31--endpoint-e93c942e-7f8f-410d-8478-21ec37bc6b0d","provider":"OpenAI","name":"OpenAI: o3 Mini","shortName":"o3 Mini","author":"OpenAI","description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the `reasoning_effort` parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Text","File"],"outputModalities":["Text"],"permaslug":"openai/o3-mini-2025-01-31","endpointId":"e93c942e-7f8f-410d-8478-21ec37bc6b0d","promptPrice":0.0000011,"completionPrice":0.0000044,"modalityScore":2,"throughput":200,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:3cc89000-ae34-4dde-9c7d-5ce009c8af0b","slug":"openai/openai-gpt-terra-latest--endpoint-3cc89000-ae34-4dde-9c7d-5ce009c8af0b","provider":"OpenAI","name":"OpenAI: GPT-5.6 Terra","shortName":"GPT-5.6 Terra","author":"OpenAI","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.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-terra-latest","endpointId":"3cc89000-ae34-4dde-9c7d-5ce009c8af0b","promptPrice":0.000002,"completionPrice":0.000012,"modalityScore":3,"throughput":43,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:1e875238-51a0-4cf4-8915-b46af937cf10","slug":"openai/openai-gpt-sol-latest--endpoint-1e875238-51a0-4cf4-8915-b46af937cf10","provider":"OpenAI","name":"OpenAI: GPT-5.6 Sol","shortName":"GPT-5.6 Sol","author":"OpenAI","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.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-sol-latest","endpointId":"1e875238-51a0-4cf4-8915-b46af937cf10","promptPrice":0.000004,"completionPrice":0.00002,"modalityScore":3,"throughput":79,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:c4f66d01-20b0-4c27-a225-438ea22fda43","slug":"openai/openai-gpt-5-mini-2025-08-07--endpoint-c4f66d01-20b0-4c27-a225-438ea22fda43","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":"c4f66d01-20b0-4c27-a225-438ea22fda43","promptPrice":2.5e-7,"completionPrice":0.000002,"modalityScore":3,"throughput":79,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:a54c5de0-89bf-4ad7-a212-cf977eed918a","slug":"openai/openai-gpt-sol-latest--endpoint-a54c5de0-89bf-4ad7-a212-cf977eed918a","provider":"OpenAI","name":"OpenAI: GPT-5.6 Sol","shortName":"GPT-5.6 Sol","author":"OpenAI","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.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-sol-latest","endpointId":"a54c5de0-89bf-4ad7-a212-cf977eed918a","promptPrice":0.000002,"completionPrice":0.00001,"modalityScore":3,"throughput":41,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:872eccb7-9c85-45fc-974a-ff7c8e2407e6","slug":"openai/openai-gpt-4-1-mini-2025-04-14--endpoint-872eccb7-9c85-45fc-974a-ff7c8e2407e6","provider":"OpenAI","name":"OpenAI: GPT-4.1 Mini","shortName":"GPT-4.1 Mini","author":"OpenAI","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.","modelVersionGroupId":null,"contextLength":1047576,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-4.1-mini-2025-04-14","endpointId":"872eccb7-9c85-45fc-974a-ff7c8e2407e6","promptPrice":4e-7,"completionPrice":0.0000016,"modalityScore":3,"throughput":33,"maxCompletionTokens":32768,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":107,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:bf8a8d37-5c1b-4343-8f0f-eee99b60c5f2","slug":"openai/openai-gpt-terra-latest--endpoint-bf8a8d37-5c1b-4343-8f0f-eee99b60c5f2","provider":"OpenAI","name":"OpenAI: GPT-5.6 Terra","shortName":"GPT-5.6 Terra","author":"OpenAI","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.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-terra-latest","endpointId":"bf8a8d37-5c1b-4343-8f0f-eee99b60c5f2","promptPrice":0.000001,"completionPrice":0.000006,"modalityScore":3,"throughput":65,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:cca25f67-7c0d-4cb9-84b2-1b53a1be000f","slug":"openai/openai-gpt-terra-latest--endpoint-cca25f67-7c0d-4cb9-84b2-1b53a1be000f","provider":"OpenAI","name":"OpenAI: GPT-5.6 Terra","shortName":"GPT-5.6 Terra","author":"OpenAI","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.","modelVersionGroupId":"20d5e431-cb58-407d-bdb0-d6cf981f1ca9","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-terra-latest","endpointId":"cca25f67-7c0d-4cb9-84b2-1b53a1be000f","promptPrice":0.000004,"completionPrice":0.000024,"modalityScore":3,"throughput":63,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":3,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:52318d70-1648-4d96-9f77-e3eefc3eecee","slug":"openai/openai-gpt-5-3-codex-20260224--endpoint-52318d70-1648-4d96-9f77-e3eefc3eecee","provider":"OpenAI","name":"OpenAI: GPT-5.3-Codex","shortName":"GPT-5.3-Codex","author":"OpenAI","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. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.\n\nBeyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.3-codex-20260224","endpointId":"52318d70-1648-4d96-9f77-e3eefc3eecee","promptPrice":0.0000035,"completionPrice":0.000028,"modalityScore":3,"throughput":77,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":4,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:bd121898-b27c-4e2c-bc92-278627465a54","slug":"openai/openai-o4-mini-2025-04-16--endpoint-bd121898-b27c-4e2c-bc92-278627465a54","provider":"OpenAI","name":"OpenAI: o4 Mini","shortName":"o4 Mini","author":"OpenAI","description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/o4-mini-2025-04-16","endpointId":"bd121898-b27c-4e2c-bc92-278627465a54","promptPrice":0.0000011,"completionPrice":0.0000044,"modalityScore":3,"throughput":100.5,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:3d6584e7-a2bb-48d6-903d-24e3d90e7e55","slug":"openai/openai-gpt-4o-2024-05-13--endpoint-3d6584e7-a2bb-48d6-903d-24e3d90e7e55","provider":"OpenAI","name":"OpenAI: GPT-4o (2024-05-13)","shortName":"GPT-4o (2024-05-13)","author":"OpenAI","description":"GPT-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.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","modelVersionGroupId":"76e36b33-358e-477a-be24-09f954fcea74","contextLength":128000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-4o-2024-05-13","endpointId":"3d6584e7-a2bb-48d6-903d-24e3d90e7e55","promptPrice":0.000005,"completionPrice":0.000015,"modalityScore":3,"throughput":74,"maxCompletionTokens":4096,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:4a8663f2-89f3-40e9-9b50-e4838fff0155","slug":"openai/openai-o3-mini-high-2025-01-31--endpoint-4a8663f2-89f3-40e9-9b50-e4838fff0155","provider":"OpenAI","name":"OpenAI: o3 Mini High","shortName":"o3 Mini High","author":"OpenAI","description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. \n\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Text","File"],"outputModalities":["Text"],"permaslug":"openai/o3-mini-high-2025-01-31","endpointId":"4a8663f2-89f3-40e9-9b50-e4838fff0155","promptPrice":0.0000011,"completionPrice":0.0000044,"modalityScore":2,"throughput":48.5,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:5acf5b3b-66dd-4ee8-8db2-2eed7d795b17","slug":"openai/openai-gpt-5-4-image-2-20260421--endpoint-5acf5b3b-66dd-4ee8-8db2-2eed7d795b17","provider":"OpenAI","name":"OpenAI: GPT-5.4 Image 2","shortName":"GPT-5.4 Image 2","author":"OpenAI","description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and visual generation within the same interaction.","modelVersionGroupId":null,"contextLength":272000,"inputModalities":["Image","Text","File"],"outputModalities":["Image","Text"],"permaslug":"openai/gpt-5.4-image-2-20260421","endpointId":"5acf5b3b-66dd-4ee8-8db2-2eed7d795b17","promptPrice":0.000008,"completionPrice":0.000015,"modalityScore":3,"throughput":43,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:60020533-2fb2-4aa1-9454-181029fd52de","slug":"openai/openai-o4-mini-high-2025-04-16--endpoint-60020533-2fb2-4aa1-9454-181029fd52de","provider":"OpenAI","name":"OpenAI: o4 Mini High","shortName":"o4 Mini High","author":"OpenAI","description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/o4-mini-high-2025-04-16","endpointId":"60020533-2fb2-4aa1-9454-181029fd52de","promptPrice":0.0000011,"completionPrice":0.0000044,"modalityScore":3,"throughput":47,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:67323917-8a17-4858-a3ad-0ec3bda83c8a","slug":"openai/openai-gpt-5-6-terra-pro-20260709--endpoint-67323917-8a17-4858-a3ad-0ec3bda83c8a","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\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":"67323917-8a17-4858-a3ad-0ec3bda83c8a","promptPrice":0.000001,"completionPrice":0.000006,"modalityScore":3,"throughput":138,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:1071a095-b9bc-40cd-8d66-88b484b1827d","slug":"openai/openai-gpt-astra-latest--endpoint-1071a095-b9bc-40cd-8d66-88b484b1827d","provider":"OpenAI","name":"OpenAI: GPT-6 Astra","shortName":"GPT-6 Astra","author":"OpenAI","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","modelVersionGroupId":"310ee917-8b07-4b12-8c29-a7a37b56cc8a","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-astra-latest","endpointId":"1071a095-b9bc-40cd-8d66-88b484b1827d","promptPrice":0.00002,"completionPrice":0.0001,"modalityScore":3,"throughput":42,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":158,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:764eb97f-8bab-4326-b29b-7a8799b00a70","slug":"openai/openai-gpt-5-1-20251113--endpoint-764eb97f-8bab-4326-b29b-7a8799b00a70","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":"764eb97f-8bab-4326-b29b-7a8799b00a70","promptPrice":0.00000125,"completionPrice":0.00001,"modalityScore":3,"throughput":39,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:355b1df4-06c8-4c36-a091-3d50477095fb","slug":"openai/openai-gpt-4--endpoint-355b1df4-06c8-4c36-a091-3d50477095fb","provider":"OpenAI","name":"OpenAI: GPT-4","shortName":"GPT-4","author":"OpenAI","description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.","modelVersionGroupId":null,"contextLength":8191,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-4","endpointId":"355b1df4-06c8-4c36-a091-3d50477095fb","promptPrice":0.00003,"completionPrice":0.00006,"modalityScore":1,"throughput":38.5,"maxCompletionTokens":4096,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"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":53,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:04c905e9-f886-468f-9410-553cd8d95c4c","slug":"openai/openai-gpt-sol-latest--endpoint-04c905e9-f886-468f-9410-553cd8d95c4c","provider":"OpenAI","name":"OpenAI: GPT-5.6 Sol","shortName":"GPT-5.6 Sol","author":"OpenAI","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.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"~openai/gpt-sol-latest","endpointId":"04c905e9-f886-468f-9410-553cd8d95c4c","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":3,"throughput":64,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:3e86b7c5-bffe-4b60-a3dd-b36451978775","slug":"openai/openai-gpt-4o-2024-11-20--endpoint-3e86b7c5-bffe-4b60-a3dd-b36451978775","provider":"OpenAI","name":"OpenAI: GPT-4o (2024-11-20)","shortName":"GPT-4o (2024-11-20)","author":"OpenAI","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 & readability. It’s also better at working with uploaded files, providing deeper insights & 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.","modelVersionGroupId":"76e36b33-358e-477a-be24-09f954fcea74","contextLength":128000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-4o-2024-11-20","endpointId":"3e86b7c5-bffe-4b60-a3dd-b36451978775","promptPrice":0.0000025,"completionPrice":0.00001,"modalityScore":3,"throughput":43.5,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:3a632f37-731d-4200-9e38-413a5f5dd39d","slug":"openai/openai-gpt-3-5-turbo--endpoint-3a632f37-731d-4200-9e38-413a5f5dd39d","provider":"OpenAI","name":"OpenAI: GPT-3.5 Turbo","shortName":"GPT-3.5 Turbo","author":"OpenAI","description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","modelVersionGroupId":null,"contextLength":16385,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-3.5-turbo","endpointId":"3a632f37-731d-4200-9e38-413a5f5dd39d","promptPrice":5e-7,"completionPrice":0.0000015,"modalityScore":1,"throughput":48,"maxCompletionTokens":4096,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"},{"id":"openrouter:486bb2d0-d2d2-4a85-a0af-7254df652cc5","slug":"openai/openai-gpt-6-astra-pro-20260903--endpoint-486bb2d0-d2d2-4a85-a0af-7254df652cc5","provider":"OpenAI","name":"OpenAI: GPT-6 Astra Pro","shortName":"GPT-6 Astra Pro","author":"OpenAI","description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\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-astra-pro-20260903","endpointId":"486bb2d0-d2d2-4a85-a0af-7254df652cc5","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":3,"throughput":79.5,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-09-22T07:00:09.370Z"}],"meta":{"totalRowCount":1386,"filterRowCount":1386,"facets":{"provider":{"rows":[{"value":"Anthropic","total":13},{"value":"OpenAI","total":95},{"value":"Google AI Studio","total":51},{"value":"DeepSeek","total":2},{"value":"MoonshotAI","total":3},{"value":"Perplexity","total":7},{"value":"MiniMax","total":13},{"value":"Mistral","total":49},{"value":"Cohere","total":7},{"value":"Amazon Bedrock","total":51},{"value":"Xiaomi","total":5},{"value":"Groq","total":8},{"value":"Together","total":21},{"value":"Fireworks","total":13},{"value":"Cerebras","total":1},{"value":"SambaNova","total":6},{"value":"DeepInfra","total":97},{"value":"Google Vertex","total":96},{"value":"Azure","total":84},{"value":"Cloudflare","total":18},{"value":"Crusoe","total":6},{"value":"Friendli","total":7},{"value":"SiliconFlow","total":40},{"value":"Chutes","total":6},{"value":"Venice","total":36},{"value":"Phala","total":20},{"value":"AtlasCloud","total":34},{"value":"NextBit","total":10},{"value":"Parasail","total":39},{"value":"Inception","total":2},{"value":"Relace","total":6},{"value":"Morph","total":6},{"value":"AionLabs","total":4},{"value":"Mancer","total":9},{"value":"GMICloud","total":23},{"value":"Ambient","total":1},{"value":"Arcee AI","total":1},{"value":"Black Forest Labs","total":7},{"value":"Inceptron","total":6},{"value":"Seed","total":14},{"value":"Sourceful","total":4},{"value":"StepFun","total":1},{"value":"StreamLake","total":23},{"value":"Upstage","total":3},{"value":"AkashML","total":6},{"value":"Alibaba Cloud Int.","total":63},{"value":"Alibaba Fast","total":1},{"value":"Alibaba OpenSource","total":1},{"value":"Amazon Bedrock (BYOK Only)","total":1},{"value":"Azure (BYOK Only)","total":1},{"value":"Baidu Qianfan","total":9},{"value":"Baidu Qianfan (fp4)","total":1},{"value":"Baidu Qianfan (fp8)","total":1},{"value":"Baseten","total":23},{"value":"Baseten (fp4)","total":2},{"value":"Baseten (fp8)","total":2},{"value":"Baseten Fast","total":2},{"value":"Claude Platform on AWS","total":9},{"value":"CoreWeave","total":18},{"value":"Darkbloom","total":8},{"value":"Decart","total":2},{"value":"Decart Fast","total":1},{"value":"Deepgram","total":2},{"value":"DeepInfra (bf16)","total":1},{"value":"DeepInfra (fp8)","total":1},{"value":"DeepInfra (Turbo)","total":5},{"value":"DeepInfra Turbo","total":2},{"value":"DeepInfra Ultra","total":1},{"value":"DekaLLM","total":7},{"value":"DigitalOcean","total":16},{"value":"Fireworks Fast","total":3},{"value":"Fish Audio","total":4},{"value":"Google Vertex (Global)","total":1},{"value":"HeyGen","total":1},{"value":"inference.net","total":5},{"value":"io.net","total":5},{"value":"Ionstream","total":2},{"value":"Krea","total":3},{"value":"Makora","total":5},{"value":"MARA","total":5},{"value":"Meta","total":7},{"value":"MiniMax Highspeed","total":3},{"value":"Modal","total":5},{"value":"ModelRun [by Modular]","total":3},{"value":"Moonshot AI Highspeed","total":1},{"value":"Morph Fast","total":2},{"value":"NEAR AI","total":1},{"value":"Nebius Token Factory","total":9},{"value":"Nex AGI","total":2},{"value":"NovitaAI","total":71},{"value":"Open Inference","total":3},{"value":"Perceptron","total":1},{"value":"Poolside","total":2},{"value":"Recraft","total":15},{"value":"Reka AI","total":6},{"value":"Runway","total":2},{"value":"Sail Research","total":10},{"value":"Sakana","total":4},{"value":"SambaNova Turbo","total":1},{"value":"SpaceXAI","total":34},{"value":"Tencent Cloud","total":5},{"value":"TypeSafe","total":1},{"value":"Unbiased","total":1},{"value":"Voyage AI by MongoDB","total":7},{"value":"Wafer","total":8},{"value":"Z.ai","total":14}],"total":1386},"author":{"rows":[{"value":"OpenAI","total":204},{"value":"Anthropic","total":90},{"value":"Google","total":137},{"value":"Meta","total":11},{"value":"DeepSeek","total":153},{"value":"Cohere","total":7},{"value":"Perplexity","total":7},{"value":"Microsoft","total":10},{"value":"Qwen","total":173},{"value":"MoonshotAI","total":66},{"value":"Amazon","total":9},{"value":"Alibaba","total":6},{"value":"Baidu","total":1},{"value":"Tencent","total":12},{"value":"ByteDance","total":15},{"value":"MiniMax","total":45},{"value":"Meituan","total":1},{"value":"Inception","total":2},{"value":"Arcee AI","total":1},{"value":"Morph","total":2},{"value":"inclusionAI","total":4},{"value":"Relace","total":2},{"value":"Nous Research","total":3},{"value":"Gryphe","total":3},{"value":"Anthracite","total":1},{"value":"Mancer","total":1},{"value":"Sao10K","total":6},{"value":"Undi","total":2},{"value":"BAAI","total":4},{"value":"Black Forest Labs","total":7},{"value":"IBM","total":3},{"value":"intfloat","total":3},{"value":"KwaiPilot","total":2},{"value":"Nex AGI","total":2},{"value":"Sentence Transformers","total":5},{"value":"Sourceful","total":4},{"value":"StepFun","total":4},{"value":"thenlper","total":2},{"value":"Upstage","total":3},{"value":"Venice","total":1},{"value":"Writer","total":1},{"value":"Xiaomi","total":16},{"value":"Aion Labs","total":4},{"value":"canopylabs","total":2},{"value":"deepgram","total":2},{"value":"Drummer","total":3},{"value":"fish-audio","total":4},{"value":"hexgrad","total":2},{"value":"heygen","total":1},{"value":"Inference Net","total":2},{"value":"krea","total":3},{"value":"kwaivgi","total":3},{"value":"Meta Llama","total":30},{"value":"Mistral AI","total":60},{"value":"Nvidia","total":17},{"value":"perceptron","total":1},{"value":"poolside","total":2},{"value":"Prism Ml","total":1},{"value":"Recraft","total":15},{"value":"rekaai","total":2},{"value":"Runway","total":2},{"value":"sakana","total":4},{"value":"sesame","total":1},{"value":"SpaceXAI","total":35},{"value":"thinkingmachines","total":7},{"value":"Typesafe","total":1},{"value":"Unbiased","total":1},{"value":"voyageai","total":7},{"value":"Z.ai","total":143}],"total":1386},"modalities":{"rows":[{"value":"Audio","total":144},{"value":"Decisions","total":1},{"value":"Embeddings","total":43},{"value":"File","total":368},{"value":"Image","total":841},{"value":"Rerank","total":6},{"value":"Speech","total":20},{"value":"Text","total":2580},{"value":"Transcription","total":25},{"value":"Video","total":317}],"total":1386},"name":{"rows":[{"value":"GLM 5.3","total":34},{"value":"GLM 5.3 Flash","total":32},{"value":"GLM 5.2","total":30},{"value":"DeepSeek V4 Flash 0731","total":29},{"value":"gpt-oss-120b","total":24},{"value":"DeepSeek V4 Pro 0813","total":24},{"value":"DeepSeek V4.1 Flash","total":23},{"value":"Kimi K2.6","total":22},{"value":"Kimi K3","total":20},{"value":"Qwen3.8 27B","total":17},{"value":"DeepSeek V4 Pro 0423","total":16},{"value":"DeepSeek V3.2","total":15},{"value":"Kimi K2.7 Code","total":15},{"value":"DeepSeek V4 Flash 0423","total":15},{"value":"Gemma 4 31B","total":14},{"value":"GLM 5.1","total":14},{"value":"gpt-oss-20b","total":13},{"value":"MiniMax M3","total":13},{"value":"Gemma 4 26B A4B","total":11},{"value":"Claude Opus 5","total":11}],"total":1386}}},"prevCursor":null,"nextCursor":50}