{"data":{"id":"mistralai","name":"Mistral AI","website":"https://mistral.ai","categories":["text","image","audio"],"docs_url":"https://docs.mistral.ai","notes":"Mistral-hosted frontier, small, code, and embedding models.","role":"lab","models":[{"id":"mistralai/mistral-large","provider_id":"mistralai","name":"Mistral Large","modalities":["text"],"context_window":128000,"family":"mistral-large","status":"active","description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1708905600,"canonical_slug":"mistralai/mistral-large","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":3,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-large-2407","provider_id":"mistralai","name":"Mistral Large 2407","modalities":["text"],"context_window":131072,"family":"mistral-large-2407","status":"active","description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1731978415,"canonical_slug":"mistralai/mistral-large-2407","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":3,"savings_pct":null,"savings_basis":null},{"id":"mistralai/codestral-2508","provider_id":"mistralai","name":"Mistral: Codestral 2508","modalities":["text"],"context_window":256000,"family":"codestral-2508","status":"active","description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1754079630,"canonical_slug":"mistralai/codestral-2508","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.45,"savings_pct":null,"savings_basis":null},{"id":"mistralai/codestral-embed-2505","provider_id":"mistralai","name":"Mistral: Codestral Embed 2505","modalities":["text"],"context_window":8192,"family":"codestral-embed-2505","status":"active","description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1761864460,"canonical_slug":"mistralai/codestral-embed-2505","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.1125,"savings_pct":null,"savings_basis":null},{"id":"mistralai/devstral-2512","provider_id":"mistralai","name":"Mistral: Devstral 2 2512","modalities":["text"],"context_window":262144,"family":"devstral-2512","status":"active","description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1765285419,"canonical_slug":"mistralai/devstral-2512","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.8,"savings_pct":null,"savings_basis":null},{"id":"mistralai/ministral-14b-2512","provider_id":"mistralai","name":"Mistral: Ministral 3 14B 2512","modalities":["text","image"],"context_window":262144,"family":"ministral-14b-2512","status":"active","description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1764681735,"canonical_slug":"mistralai/ministral-14b-2512","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.2,"savings_pct":null,"savings_basis":null},{"id":"mistralai/ministral-3b-2512","provider_id":"mistralai","name":"Mistral: Ministral 3 3B 2512","modalities":["text","image"],"context_window":131072,"family":"ministral-3b-2512","status":"active","description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1764681560,"canonical_slug":"mistralai/ministral-3b-2512","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.1,"savings_pct":null,"savings_basis":null},{"id":"mistralai/ministral-8b-2512","provider_id":"mistralai","name":"Mistral: Ministral 3 8B 2512","modalities":["text","image"],"context_window":262144,"family":"ministral-8b-2512","status":"active","description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1764681654,"canonical_slug":"mistralai/ministral-8b-2512","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.15,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-embed-2312","provider_id":"mistralai","name":"Mistral: Mistral Embed 2312","modalities":["text"],"context_window":8192,"family":"mistral-embed-2312","status":"active","description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively...","architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1761944622,"canonical_slug":"mistralai/mistral-embed-2312","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.075,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-large-2512","provider_id":"mistralai","name":"Mistral: Mistral Large 3 2512","modalities":["text","image"],"context_window":262144,"family":"mistral-large-2512","status":"active","description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1764624472,"canonical_slug":"mistralai/mistral-large-2512","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.75,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-large-4-0","provider_id":"mistralai","name":"Mistral: Mistral Large 4","modalities":["text","image"],"context_window":1048576,"family":"mistral-large-4-0","status":"active","description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"created_at":1791294122,"canonical_slug":"mistralai/mistral-large-4-0-20261006","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":1.05,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-medium-3","provider_id":"mistralai","name":"Mistral: Mistral Medium 3","modalities":["text","image"],"context_window":131072,"family":"mistral-medium-3","status":"active","description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1746627341,"canonical_slug":"mistralai/mistral-medium-3","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.8,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-medium-3.1","provider_id":"mistralai","name":"Mistral: Mistral Medium 3.1","modalities":["text","image"],"context_window":131072,"family":"mistral-medium-3.1","status":"active","description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1755095639,"canonical_slug":"mistralai/mistral-medium-3.1","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.8,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-medium-3-5","provider_id":"mistralai","name":"Mistral: Mistral Medium 3.5","modalities":["text","image"],"context_window":262144,"family":"mistral-medium-3-5","status":"active","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1777570439,"canonical_slug":"mistralai/mistral-medium-3.5-20260430","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":3,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-medium-3-5:batch","provider_id":"mistralai","name":"Mistral: Mistral Medium 3.5 (batch)","modalities":["text","image"],"context_window":262144,"family":"mistral-medium-3-5","status":"active","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1777570439,"canonical_slug":"mistralai/mistral-medium-3.5-20260430","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-nemo","provider_id":"mistralai","name":"Mistral: Mistral Nemo","modalities":["text"],"context_window":131072,"family":"mistral-nemo","status":"active","description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1721347200,"canonical_slug":"mistralai/mistral-nemo","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"ionet","cheapest_provider_name":"Io Net","cheapest_price":0.01782,"savings_pct":88.1,"savings_basis":"lab"},{"id":"mistralai/mistral-small-24b-instruct-2501","provider_id":"mistralai","name":"Mistral: Mistral Small 3","modalities":["text"],"context_window":32768,"family":"mistral-small-24b-instruct-2501","status":"active","description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"created_at":1738255409,"canonical_slug":"mistralai/mistral-small-24b-instruct-2501","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.0575,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-small-3.1-24b-instruct","provider_id":"mistralai","name":"Mistral: Mistral Small 3.1 24B","modalities":["text","image"],"context_window":128000,"family":"mistral-small-3.1-24b-instruct","status":"active","description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1742238937,"canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"cloudflare","cheapest_provider_name":"Cloudflare","cheapest_price":0.402,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-small-3.2-24b-instruct","provider_id":"mistralai","name":"Mistral: Mistral Small 3.2 24B","modalities":["image","text"],"context_window":256000,"family":"mistral-small-3.2-24b-instruct","status":"active","description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1750443016,"canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.10625,"savings_pct":29.2,"savings_basis":"lab"},{"id":"mistralai/mistral-small-2603","provider_id":"mistralai","name":"Mistral: Mistral Small 4","modalities":["text","image"],"context_window":262144,"family":"mistral-small-2603","status":"active","description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1773695685,"canonical_slug":"mistralai/mistral-small-2603","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.2625,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mixtral-8x22b-instruct","provider_id":"mistralai","name":"Mistral: Mixtral 8x22B Instruct","modalities":["text"],"context_window":65536,"family":"mixtral-8x22b-instruct","status":"active","description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1713312000,"canonical_slug":"mistralai/mixtral-8x22b-instruct","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":3,"savings_pct":null,"savings_basis":null},{"id":"mistralai/mistral-saba","provider_id":"mistralai","name":"Mistral: Saba","modalities":["text"],"context_window":32768,"family":"mistral-saba","status":"active","description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1739803239,"canonical_slug":"mistralai/mistral-saba-2502","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":0.3,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-mini-3b-2507","provider_id":"mistralai","name":"Mistral: Voxtral Mini 3B 2507","modalities":["audio"],"context_window":0,"family":"voxtral-mini-3b-2507","status":"active","description":"Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1786653980,"canonical_slug":"mistralai/voxtral-mini-3b-2507-20260813","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.0000166667,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-mini-transcribe","provider_id":"mistralai","name":"Mistral: Voxtral Mini Transcribe","modalities":["audio"],"context_window":16384,"family":"voxtral-mini-transcribe","status":"active","description":"Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,...","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1778877024,"canonical_slug":"mistralai/voxtral-mini-transcribe-2602","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":37.5,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-mini-transcribe-3-0","provider_id":"mistralai","name":"Mistral: Voxtral Mini Transcribe 3","modalities":["audio"],"context_window":65536,"family":"voxtral-mini-transcribe-3-0","status":"active","description":"Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms....","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1792512796,"canonical_slug":"mistralai/voxtral-mini-transcribe-3-0-20261020","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":43.749975,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-mini-tts-2603","provider_id":"mistralai","name":"Mistral: Voxtral Mini TTS","modalities":["text","audio"],"context_window":4096,"family":"voxtral-mini-tts-2603","status":"active","description":"Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.","architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1776571337,"canonical_slug":"mistralai/voxtral-mini-tts-2603","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":12,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-small-24b-2507","provider_id":"mistralai","name":"Mistral: Voxtral Small 24B 2507","modalities":["text","audio"],"context_window":32768,"family":"voxtral-small-24b-2507","status":"active","description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1761835144,"canonical_slug":"mistralai/voxtral-small-24b-2507","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.00005,"savings_pct":100,"savings_basis":"lab"},{"id":"mistralai/voxtral-small-24b-2507-stt","provider_id":"mistralai","name":"Mistral: Voxtral Small 24B 2507 STT","modalities":["audio"],"context_window":0,"family":"voxtral-small-24b-2507-stt","status":"active","description":"Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1786654002,"canonical_slug":"mistralai/voxtral-small-24b-2507-stt-20260813","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":37.5,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-small-transcribe-3-0","provider_id":"mistralai","name":"Mistral: Voxtral Small Transcribe 3","modalities":["audio"],"context_window":65536,"family":"voxtral-small-transcribe-3-0","status":"active","description":"Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited...","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1792512812,"canonical_slug":"mistralai/voxtral-small-transcribe-3-0-20261020","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":50.000025,"savings_pct":null,"savings_basis":null},{"id":"mistralai/voxtral-mini-tts-3-0","provider_id":"mistralai","name":"Mistral: Voxtral TTS 3","modalities":["text","audio"],"context_window":4096,"family":"voxtral-mini-tts-3-0","status":"active","description":"Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...","architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Mistral","instruct_type":null},"supported_parameters":[],"created_at":1792512813,"canonical_slug":"mistralai/voxtral-mini-tts-3-0-20261020","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"mistralai","creator_name":"Mistral AI","cheapest_provider":"mistralai","cheapest_provider_name":"Mistral AI","cheapest_price":9.75,"savings_pct":null,"savings_basis":null}]}}