{"data":[{"id":"anthropic/anthropic/claude-opus-4.5--variant-standard--seq-82","slug":"anthropic/anthropic/claude-opus-4.5--variant-standard","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":42,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-opus-4--variant-standard--seq-86","slug":"anthropic/anthropic/claude-opus-4--variant-standard","provider":"Anthropic","name":"Anthropic: Claude Opus 4","shortName":"Claude Opus 4","author":"Anthropic","description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4-opus-20250522","endpointId":"9ea0cd22-4494-4a94-9199-c83c992bdbe1","promptPrice":0.000015,"completionPrice":0.000075,"modalityScore":3,"throughput":3,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-opus-4.6-fast--variant-standard--seq-79","slug":"anthropic/anthropic/claude-opus-4.6-fast--variant-standard","provider":"Anthropic","name":"Anthropic: Claude Opus 4.6 (Fast)","shortName":"Claude Opus 4.6 (Fast)","author":"Anthropic","description":"Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","modelVersionGroupId":null,"contextLength":1000000,"inputModalities":["Text","Image"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.6-opus-fast-20260407","endpointId":"4fa9f1b5-21cc-41c7-a053-9d9728cbbc54","promptPrice":0.00003,"completionPrice":0.00015,"modalityScore":2,"throughput":57,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-opus-4.7--variant-standard--seq-78","slug":"anthropic/anthropic/claude-opus-4.7--variant-standard","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"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.7-opus-20260416","endpointId":"71784905-0c14-4c62-851a-c998ae9a222c","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":2,"throughput":48,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-opus-4.1--variant-standard--seq-85","slug":"anthropic/anthropic/claude-opus-4.1--variant-standard","provider":"Anthropic","name":"Anthropic: Claude Opus 4.1","shortName":"Claude Opus 4.1","author":"Anthropic","description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.1-opus-20250805","endpointId":"ca4e491c-208c-4bd0-b808-35e0ad56bc52","promptPrice":0.000015,"completionPrice":0.000075,"modalityScore":3,"throughput":14,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-sonnet-4--variant-standard--seq-87","slug":"anthropic/anthropic/claude-sonnet-4--variant-standard","provider":"Anthropic","name":"Anthropic: Claude Sonnet 4","shortName":"Claude Sonnet 4","author":"Anthropic","description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","modelVersionGroupId":null,"contextLength":1000000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4-sonnet-20250522","endpointId":"d8dcebf2-d75f-4769-af19-cfc028a4cb7d","promptPrice":0.000003,"completionPrice":0.000015,"modalityScore":3,"throughput":40,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-sonnet-4.5--variant-standard--seq-84","slug":"anthropic/anthropic/claude-sonnet-4.5--variant-standard","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":"252ef628-b840-4ff4-948b-86e24f080256","promptPrice":0.000003,"completionPrice":0.000015,"modalityScore":3,"throughput":37,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","top_k","response_format"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-sonnet-4.6--variant-standard--seq-80","slug":"anthropic/anthropic/claude-sonnet-4.6--variant-standard","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"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.6-sonnet-20260217","endpointId":"6d408764-7dd7-4626-bb87-a6cc1589bc86","promptPrice":0.000003,"completionPrice":0.000015,"modalityScore":2,"throughput":41,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-haiku-4.5--variant-standard--seq-83","slug":"anthropic/anthropic/claude-haiku-4.5--variant-standard","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":["Image","Text"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.5-haiku-20251001","endpointId":"41d2915a-92e6-4993-b537-210b4e10cba8","promptPrice":0.000001,"completionPrice":0.000005,"modalityScore":2,"throughput":57,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"anthropic/anthropic/claude-opus-4.6--variant-standard--seq-81","slug":"anthropic/anthropic/claude-opus-4.6--variant-standard","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"],"outputModalities":["Text"],"permaslug":"anthropic/claude-4.6-opus-20260205","endpointId":"7dd650a5-2f59-4766-90e5-62845c4edf63","promptPrice":0.000005,"completionPrice":0.000025,"modalityScore":2,"throughput":34,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"scrapedAt":"2026-05-10T07:00:01.967Z"},{"id":"openai/openai/gpt-4o-2024-11-20--variant-standard--seq-629","slug":"openai/openai/gpt-4o-2024-11-20--variant-standard","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":6,"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","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-mini--variant-standard--seq-632","slug":"openai/openai/gpt-4o-mini--variant-standard","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":37,"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","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4-turbo-preview--variant-standard--seq-636","slug":"openai/openai/gpt-4-turbo-preview--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4 Turbo Preview","shortName":"GPT-4 Turbo Preview","author":"OpenAI","description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.\n\n**Note:** heavily rate limited by OpenAI while in preview.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-4-turbo-preview","endpointId":"003933da-395a-48eb-86a3-0c4ec486d67f","promptPrice":0.00001,"completionPrice":0.00003,"modalityScore":1,"throughput":null,"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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5--variant-standard--seq-613","slug":"openai/openai/gpt-5--variant-standard","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":65,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.1--variant-standard--seq-598","slug":"openai/openai/gpt-5.1--variant-standard","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":51,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5-image-mini--variant-standard--seq-605","slug":"openai/openai/gpt-5-image-mini--variant-standard","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":122,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o1--variant-standard--seq-628","slug":"openai/openai/o1--variant-standard","provider":"OpenAI","name":"OpenAI: o1","shortName":"o1","author":"OpenAI","description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/o1-2024-12-17","endpointId":"82738f61-f3cb-44a5-b5d1-e6787ae64e3b","promptPrice":0.000015,"completionPrice":0.00006,"modalityScore":3,"throughput":136,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o--variant-standard--seq-634","slug":"openai/openai/gpt-4o--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4o","shortName":"GPT-4o","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","endpointId":"452a72a0-2c24-4e31-98cb-d6cc1084fb99","promptPrice":0.0000025,"completionPrice":0.00001,"modalityScore":3,"throughput":78,"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","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/text-embedding-3-large--variant-standard--seq-603","slug":"openai/openai/text-embedding-3-large--variant-standard","provider":"OpenAI","name":"OpenAI: Text Embedding 3 Large","shortName":"Text Embedding 3 Large","author":"OpenAI","description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","modelVersionGroupId":null,"contextLength":8192,"inputModalities":["Text"],"outputModalities":["Embeddings"],"permaslug":"openai/text-embedding-3-large","endpointId":"8083d8ef-5e78-4124-8536-f65ba99e2a8a","promptPrice":1.3e-7,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.2-codex--variant-standard--seq-593","slug":"openai/openai/gpt-5.2-codex--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.2-Codex","shortName":"GPT-5.2-Codex","author":"OpenAI","description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.2-codex-20260114","endpointId":"dff70494-a1eb-4be2-b61f-9b2277db56c9","promptPrice":0.00000175,"completionPrice":0.000014,"modalityScore":2,"throughput":84,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-3.5-turbo-instruct--variant-standard--seq-638","slug":"openai/openai/gpt-3.5-turbo-instruct--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-3.5 Turbo Instruct","shortName":"GPT-3.5 Turbo Instruct","author":"OpenAI","description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","modelVersionGroupId":null,"contextLength":4095,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-3.5-turbo-instruct","endpointId":"39594b4d-6c7e-4ccd-aeed-79f9b3ca5819","promptPrice":0.0000015,"completionPrice":0.000002,"modalityScore":1,"throughput":73,"maxCompletionTokens":4096,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o4-mini-deep-research--variant-standard--seq-608","slug":"openai/openai/o4-mini-deep-research--variant-standard","provider":"OpenAI","name":"OpenAI: o4 Mini Deep Research","shortName":"o4 Mini Deep Research","author":"OpenAI","description":"o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/o4-mini-deep-research-2025-06-26","endpointId":"97f9f7c3-9e55-4f6d-8de4-459d4f23e2a9","promptPrice":0.000002,"completionPrice":0.000008,"modalityScore":3,"throughput":75.5,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.5--variant-standard--seq-581","slug":"openai/openai/gpt-5.5--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.5","shortName":"GPT-5.5","author":"OpenAI","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","modelVersionGroupId":"c59971be-c6bc-4199-9192-95e9dc48cb9e","contextLength":1050000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.5-20260423","endpointId":"58e5b336-423e-430b-a2ab-8bc353f0c51b","promptPrice":0.000005,"completionPrice":0.00003,"modalityScore":3,"throughput":41,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o3--variant-standard--seq-618","slug":"openai/openai/o3--variant-standard","provider":"OpenAI","name":"OpenAI: o3","shortName":"o3","author":"OpenAI","description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Image","Text","File"],"outputModalities":["Text"],"permaslug":"openai/o3-2025-04-16","endpointId":"42e72619-d01c-411c-a201-f991644768b7","promptPrice":0.000002,"completionPrice":0.000008,"modalityScore":3,"throughput":57,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4-0314--variant-standard--seq-640","slug":"openai/openai/gpt-4-0314--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4 (older v0314)","shortName":"GPT-4 (older v0314)","author":"OpenAI","description":"GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.","modelVersionGroupId":null,"contextLength":8191,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-4-0314","endpointId":"69206fec-9f6f-4338-9919-5ed90134c376","promptPrice":0.00003,"completionPrice":0.00006,"modalityScore":1,"throughput":null,"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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-2024-05-13--variant-standard--seq-633","slug":"openai/openai/gpt-4o-2024-05-13--variant-standard","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":83,"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","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-3.5-turbo--variant-standard--seq-642","slug":"openai/openai/gpt-3.5-turbo--variant-standard","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":67,"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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.4-image-2--variant-standard--seq-582","slug":"openai/openai/gpt-5.4-image-2--variant-standard","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":38,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-mini-search-preview--variant-standard--seq-624","slug":"openai/openai/gpt-4o-mini-search-preview--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4o-mini Search Preview","shortName":"GPT-4o-mini Search Preview","author":"OpenAI","description":"GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-4o-mini-search-preview-2025-03-11","endpointId":"5154b382-e458-4539-bf6d-cbadfbaa0600","promptPrice":1.5e-7,"completionPrice":6e-7,"modalityScore":1,"throughput":44,"maxCompletionTokens":16384,"supportedParameters":["web_search_options","max_tokens","response_format","structured_outputs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-chat-latest--variant-standard--seq-576","slug":"openai/openai/gpt-chat-latest--variant-standard","provider":"OpenAI","name":"OpenAI: GPT Chat Latest","shortName":"GPT Chat Latest","author":"OpenAI","description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.\n\nFor more info, see: https://developers.openai.com/api/docs/models/chat-latest","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/gpt-chat-latest-20260505","endpointId":"144906de-89e6-4ba4-a986-640af2562cfa","promptPrice":0.000005,"completionPrice":0.00003,"modalityScore":3,"throughput":94,"maxCompletionTokens":128000,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4--variant-standard--seq-641","slug":"openai/openai/gpt-4--variant-standard","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":23,"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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o4-mini-high--variant-standard--seq-617","slug":"openai/openai/o4-mini-high--variant-standard","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":139,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.1-codex-mini--variant-standard--seq-601","slug":"openai/openai/gpt-5.1-codex-mini--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.1-Codex-Mini","shortName":"GPT-5.1-Codex-Mini","author":"OpenAI","description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.1-codex-mini-20251113","endpointId":"27923ab8-2d0e-47ac-b04c-fc79d77ddbd5","promptPrice":2.5e-7,"completionPrice":0.000002,"modalityScore":2,"throughput":52,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o3-mini-high--variant-standard--seq-626","slug":"openai/openai/o3-mini-high--variant-standard","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":255.5,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.4-nano--variant-standard--seq-585","slug":"openai/openai/gpt-5.4-nano--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.4 Nano","shortName":"GPT-5.4 Nano","author":"OpenAI","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["File","Image","Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.4-nano-20260317","endpointId":"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f","promptPrice":2e-7,"completionPrice":0.00000125,"modalityScore":3,"throughput":50,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-mini-tts-2025-12-15--variant-standard--seq-583","slug":"openai/openai/gpt-4o-mini-tts-2025-12-15--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4o Mini TTS","shortName":"GPT-4o Mini TTS","author":"OpenAI","description":"GPT-4o Mini TTS is OpenAI's cost-efficient text-to-speech model. It converts text input into natural-sounding audio output, supporting a variety of voices and tones.","modelVersionGroupId":null,"contextLength":4096,"inputModalities":["Text"],"outputModalities":["Speech"],"permaslug":"openai/gpt-4o-mini-tts-2025-12-15","endpointId":"7ebe5a0b-2ee9-494b-9284-e026cd85ecb9","promptPrice":6e-7,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/sora-2-pro--variant-standard--seq-584","slug":"openai/openai/sora-2-pro--variant-standard","provider":"OpenAI","name":"OpenAI: Sora 2 Pro","shortName":"Sora 2 Pro","author":"OpenAI","description":"OpenAI's flagship video generation model, delivering production-quality video with physics-accurate motion, synchronized audio, and world-state persistence across shots. Sora 2 Pro follows intricate multi-shot instructions while maintaining consistent spatial relationships — objects don't disappear or change shape between cuts. Supports text-to-video and image-to-video, with synchronized background soundscapes, speech, and sound effects. Includes advanced content safety with C2PA metadata provenance and SynthID-style watermarking.","modelVersionGroupId":null,"contextLength":null,"inputModalities":["Text","Image"],"outputModalities":["Video"],"permaslug":"openai/sora-2-pro-20260320","endpointId":"99fcd931-7ba8-47c0-af5a-70c4ef96dbcc","promptPrice":0,"completionPrice":0,"modalityScore":3,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-audio-mini--variant-standard--seq-592","slug":"openai/openai/gpt-audio-mini--variant-standard","provider":"OpenAI","name":"OpenAI: GPT Audio Mini","shortName":"GPT Audio Mini","author":"OpenAI","description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million tokens and output is priced at $2.40 per million tokens.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text","Audio"],"outputModalities":["Text","Audio"],"permaslug":"openai/gpt-audio-mini","endpointId":"53417803-f19f-4905-af00-f7e023d09858","promptPrice":6e-7,"completionPrice":0.0000024,"modalityScore":2,"throughput":3,"maxCompletionTokens":16384,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tool_choice","tools"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5-mini--variant-standard--seq-614","slug":"openai/openai/gpt-5-mini--variant-standard","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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-transcribe--variant-standard--seq-579","slug":"openai/openai/gpt-4o-transcribe--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4o Transcribe","shortName":"GPT-4o Transcribe","author":"OpenAI","description":"GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Audio"],"outputModalities":["Transcription"],"permaslug":"openai/gpt-4o-transcribe","endpointId":"7cfa86fe-92c1-4c46-a15d-fde46cedb5ed","promptPrice":0.0000025,"completionPrice":0.00001,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/text-embedding-ada-002--variant-standard--seq-602","slug":"openai/openai/text-embedding-ada-002--variant-standard","provider":"OpenAI","name":"OpenAI: Text Embedding Ada 002","shortName":"Text Embedding Ada 002","author":"OpenAI","description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","modelVersionGroupId":null,"contextLength":8192,"inputModalities":["Text"],"outputModalities":["Embeddings"],"permaslug":"openai/text-embedding-ada-002","endpointId":"1a2e0fcd-fb63-48b8-8257-5d2891aa8d25","promptPrice":1e-7,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.2-pro--variant-standard--seq-595","slug":"openai/openai/gpt-5.2-pro--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.2 Pro","shortName":"GPT-5.2 Pro","author":"OpenAI","description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. 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-5.2-pro-20251211","endpointId":"1abae580-6f7a-4092-ae6c-b87ce6067f61","promptPrice":0.000021,"completionPrice":0.000168,"modalityScore":3,"throughput":3,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/text-embedding-3-small--variant-standard--seq-604","slug":"openai/openai/text-embedding-3-small--variant-standard","provider":"OpenAI","name":"OpenAI: Text Embedding 3 Small","shortName":"Text Embedding 3 Small","author":"OpenAI","description":" text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","modelVersionGroupId":null,"contextLength":8192,"inputModalities":["Text"],"outputModalities":["Embeddings"],"permaslug":"openai/text-embedding-3-small","endpointId":"d88ee4ad-6cb6-4b9e-b84c-5ca8a4c58e58","promptPrice":2e-8,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5-nano--variant-standard--seq-615","slug":"openai/openai/gpt-5-nano--variant-standard","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":57,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.1-codex--variant-standard--seq-600","slug":"openai/openai/gpt-5.1-codex--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-5.1-Codex","shortName":"GPT-5.1-Codex","author":"OpenAI","description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","modelVersionGroupId":null,"contextLength":400000,"inputModalities":["Text","Image"],"outputModalities":["Text"],"permaslug":"openai/gpt-5.1-codex-20251113","endpointId":"58caabab-f2a1-4a27-b098-b46b924efd27","promptPrice":0.00000125,"completionPrice":0.00001,"modalityScore":2,"throughput":51,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/o1-pro--variant-standard--seq-623","slug":"openai/openai/o1-pro--variant-standard","provider":"OpenAI","name":"OpenAI: o1-pro","shortName":"o1-pro","author":"OpenAI","description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","modelVersionGroupId":null,"contextLength":200000,"inputModalities":["Text","Image","File"],"outputModalities":["Text"],"permaslug":"openai/o1-pro","endpointId":"046ae30d-fe99-44b4-b020-21127e4342c7","promptPrice":0.00015,"completionPrice":0.0006,"modalityScore":3,"throughput":14.5,"maxCompletionTokens":100000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/whisper-1--variant-standard--seq-578","slug":"openai/openai/whisper-1--variant-standard","provider":"OpenAI","name":"OpenAI: Whisper 1","shortName":"Whisper 1","author":"OpenAI","description":"Whisper is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.","modelVersionGroupId":null,"contextLength":null,"inputModalities":["Audio"],"outputModalities":["Transcription"],"permaslug":"openai/whisper-1","endpointId":"5f7f832c-14e5-440e-b651-d81d9e81988d","promptPrice":0.006,"completionPrice":0,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4o-mini-transcribe--variant-standard--seq-577","slug":"openai/openai/gpt-4o-mini-transcribe--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4o Mini Transcribe","shortName":"GPT-4o Mini Transcribe","author":"OpenAI","description":"GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that benefit from token-level billing transparency at a lower cost point.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Audio"],"outputModalities":["Transcription"],"permaslug":"openai/gpt-4o-mini-transcribe","endpointId":"9c16597f-7a17-49be-be5b-4070220af620","promptPrice":0.00000125,"completionPrice":0.000005,"modalityScore":2,"throughput":null,"maxCompletionTokens":null,"supportedParameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"scrapedAt":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-4-1106-preview--variant-standard--seq-637","slug":"openai/openai/gpt-4-1106-preview--variant-standard","provider":"OpenAI","name":"OpenAI: GPT-4 Turbo (older v1106)","shortName":"GPT-4 Turbo (older v1106)","author":"OpenAI","description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to April 2023.","modelVersionGroupId":null,"contextLength":128000,"inputModalities":["Text"],"outputModalities":["Text"],"permaslug":"openai/gpt-4-1106-preview","endpointId":"8744de26-f64f-41cf-bd0e-950a83d1a923","promptPrice":0.00001,"completionPrice":0.00003,"modalityScore":1,"throughput":null,"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":"2026-05-10T07:00:10.962Z"},{"id":"openai/openai/gpt-5.3-codex--variant-standard--seq-590","slug":"openai/openai/gpt-5.3-codex--variant-standard","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":"75bb5ca0-7b08-4f1a-aca5-aa2bbf44d98e","promptPrice":0.00000175,"completionPrice":0.000014,"modalityScore":3,"throughput":61,"maxCompletionTokens":128000,"supportedParameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"scrapedAt":"2026-05-10T07:00:10.962Z"}],"meta":{"totalRowCount":866,"filterRowCount":866,"facets":{"provider":{"rows":[{"value":"Anthropic","total":10},{"value":"OpenAI","total":67},{"value":"Google AI Studio","total":19},{"value":"DeepSeek","total":2},{"value":"xAI","total":11},{"value":"MoonshotAI","total":2},{"value":"Z.AI","total":13},{"value":"Perplexity","total":7},{"value":"MiniMax","total":8},{"value":"Mistral","total":24},{"value":"Cohere","total":7},{"value":"AI21","total":1},{"value":"Inflection","total":2},{"value":"Amazon Bedrock","total":22},{"value":"Alibaba Cloud","total":43},{"value":"Xiaomi","total":5},{"value":"Groq","total":10},{"value":"Together","total":28},{"value":"Fireworks","total":8},{"value":"Cerebras","total":4},{"value":"SambaNova","total":7},{"value":"DeepInfra","total":82},{"value":"Google Vertex","total":47},{"value":"Azure","total":33},{"value":"NVIDIA","total":6},{"value":"Cloudflare","total":14},{"value":"Nebius","total":15},{"value":"BaseTen","total":4},{"value":"Friendli","total":7},{"value":"SiliconFlow","total":33},{"value":"Novita","total":74},{"value":"Chutes","total":8},{"value":"Venice","total":30},{"value":"Phala","total":13},{"value":"AtlasCloud","total":47},{"value":"Weights and Biases","total":13},{"value":"NextBit","total":16},{"value":"Parasail","total":33},{"value":"Inception","total":1},{"value":"Relace","total":2},{"value":"Morph","total":5},{"value":"Infermatic","total":2},{"value":"AionLabs","total":4},{"value":"Mancer","total":5},{"value":"Liquid","total":2},{"value":"OpenInference","total":3},{"value":"GMICloud","total":5},{"value":"Switchpoint","total":1},{"value":"Featherless","total":1},{"value":"Ambient","total":1},{"value":"Arcee AI","total":2},{"value":"Black Forest Labs","total":4},{"value":"Clarifai","total":1},{"value":"Inceptron","total":4},{"value":"Io Net","total":3},{"value":"Mara","total":1},{"value":"ModelRun","total":2},{"value":"Seed","total":8},{"value":"Sourceful","total":5},{"value":"Stealth","total":1},{"value":"StepFun","total":1},{"value":"StreamLake","total":2},{"value":"Upstage","total":1},{"value":"AkashML","total":6},{"value":"Baidu","total":5},{"value":"DekaLLM","total":5},{"value":"Ionstream","total":1},{"value":"Poolside","total":2},{"value":"Recraft","total":3},{"value":"Reka","total":2}],"total":866},"author":{"rows":[{"value":"OpenAI","total":130},{"value":"Anthropic","total":36},{"value":"xAI","total":11},{"value":"Google","total":66},{"value":"Meta","total":44},{"value":"DeepSeek","total":61},{"value":"Mistral","total":37},{"value":"Cohere","total":7},{"value":"Perplexity","total":7},{"value":"NVIDIA","total":12},{"value":"Microsoft","total":4},{"value":"Qwen","total":166},{"value":"Z.AI","total":68},{"value":"MoonshotAI","total":39},{"value":"Amazon","total":5},{"value":"Alibaba","total":3},{"value":"Baidu","total":7},{"value":"Tencent","total":2},{"value":"ByteDance","total":9},{"value":"AI21","total":1},{"value":"MiniMax","total":35},{"value":"Inflection","total":2},{"value":"Liquid","total":3},{"value":"Inception","total":1},{"value":"AionLabs","total":4},{"value":"Arcee AI","total":9},{"value":"AllenAI","total":1},{"value":"Deep Cogito","total":1},{"value":"Morph","total":2},{"value":"inclusionAI","total":3},{"value":"Relace","total":2},{"value":"Switchpoint","total":1},{"value":"Nous Research","total":6},{"value":"Gryphe","total":3},{"value":"Anthracite","total":1},{"value":"AlfredPros","total":1},{"value":"Mancer","total":1},{"value":"Alpindale","total":1},{"value":"Sao10K","total":7},{"value":"Undi","total":2},{"value":"TheDrummer","total":5},{"value":"BAAI","total":4},{"value":"Black Forest Labs","total":4},{"value":"Essential AI","total":1},{"value":"IBM","total":2},{"value":"intfloat","total":3},{"value":"KwaiPilot","total":2},{"value":"Nex AGI","total":1},{"value":"Prime Intellect","total":1},{"value":"Sentence Transformers","total":5},{"value":"Sourceful","total":5},{"value":"StepFun","total":4},{"value":"thenlper","total":2},{"value":"Upstage","total":1},{"value":"Venice","total":1},{"value":"Writer","total":1},{"value":"Xiaomi","total":7},{"value":"canopylabs","total":1},{"value":"hexgrad","total":1},{"value":"kwaivgi","total":3},{"value":"openrouter","total":1},{"value":"poolside","total":2},{"value":"recraft","total":3},{"value":"rekaai","total":2},{"value":"sesame","total":1},{"value":"zyphra","total":2}],"total":866},"modalities":{"rows":[{"value":"Audio","total":40},{"value":"Embeddings","total":30},{"value":"File","total":107},{"value":"Image","total":383},{"value":"Rerank","total":3},{"value":"Speech","total":8},{"value":"Text","total":1653},{"value":"Transcription","total":6},{"value":"Video","total":112}],"total":866},"name":{"rows":[{"value":"MiniMax M2.5","total":18},{"value":"gpt-oss-120b","total":18},{"value":"Kimi K2.6","total":17},{"value":"GLM 5","total":17},{"value":"GLM 5.1","total":15},{"value":"Llama 3.3 70B Instruct","total":14},{"value":"Kimi K2.5","total":14},{"value":"gpt-oss-20b","total":12},{"value":"Qwen3.5 397B A17B","total":12},{"value":"Gemma 4 26B A4B","total":11},{"value":"Qwen3 235B A22B Instruct 2507","total":11},{"value":"GLM 4.7","total":10},{"value":"DeepSeek V4 Pro","total":9},{"value":"DeepSeek V3.1","total":9},{"value":"DeepSeek V3.2","total":9},{"value":"Qwen3 Coder 480B A35B","total":9},{"value":"Qwen3.5-35B-A3B","total":8},{"value":"Llama 3.1 8B Instruct","total":8},{"value":"DeepSeek V4 Flash","total":8},{"value":"Gemma 4 31B","total":7}],"total":866}}},"prevCursor":null,"nextCursor":50}