Models
One name per model, however many providers serve it.
Mistral: Pixtral Large 2502
Accepts- Text
- Image
Creates- Text
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following Pixtral Large 2411.
mistralai/pixtral-large-2502Nov 20, 2026128K context720,776 Toman/M input tokens2,162,328 Toman/M output tokensMistral: Voxtral TTS 3
Accepts- Text
Creates- Audio
Voxtral TTS 3 is Mistral's text-to-speech model.
mistralai/voxtral-mini-tts-3-0Oct 20, 20264K context66 voicesMP3 · WAV4,685 Toman per 1,000 charactersMistral: Voxtral Small Transcribe 3
Accepts- Audio
Creates- Text
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.
mistralai/voxtral-small-transcribe-3-0Oct 20, 202666K contextText only, no times1,442 Toman a minute of audioMistral: Voxtral Mini Transcribe 3
Accepts- Audio
Creates- Text
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.
mistralai/voxtral-mini-transcribe-3-0Oct 20, 202666K contextText only, no times1,261 Toman a minute of audioMistral: Mistral Large 4
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningMistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
mistralai/mistral-large-4-0Oct 6, 20261M context252,784 Toman/M input tokens758,352 Toman/M output tokensMistral: Voxtral Small 24B 2507 STT
Accepts- Audio
Creates- Text
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.
mistralai/voxtral-small-24b-2507-sttAug 13, 2026With segment and word times1,081 Toman a minute of audioMistral: Voxtral Mini 3B 2507
Accepts- Audio
Creates- Text
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.
mistralai/voxtral-mini-3b-2507Aug 13, 2026With segment and word times361 Toman a minute of audioMistral: Voxtral Mini Transcribe
Accepts- Audio
Creates- Text
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.
mistralai/voxtral-mini-transcribeMay 15, 202616K contextWith segment and word times1,081 Toman a minute of audioMistral: Mistral Medium 3.5
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONReasoningMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
mistralai/mistral-medium-3-5Apr 30, 2026262K context543,144 Toman/M input tokens2,705,472 Toman/M output tokensMistral: Voxtral Mini TTS
Accepts- Text
Creates- Audio
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.
mistralai/voxtral-mini-tts-2603Apr 19, 20264K context30 voicesMP3 · WAV5,766 Toman per 1,000 charactersMistral: Mistral Small 4
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
mistralai/mistral-small-2603Mar 16, 2026262K context54,656 Toman/M input tokens218,624 Toman/M output tokensMistral: Devstral 2 2512
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONDevstral 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.
mistralai/devstral-2512Dec 9, 2025262K context146,888 Toman/M input tokens720,776 Toman/M output tokensMistral: Ministral 3 14B 2512
Accepts- Text
- Image
Creates- Text
ToolsJSONThe 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.
mistralai/ministral-14b-2512Dec 2, 2025262K context75,152 Toman/M input tokens75,152 Toman/M output tokensMistral: Ministral 3 8B 2512
Accepts- Text
- Image
Creates- Text
ToolsJSONA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
mistralai/ministral-8b-2512Dec 2, 2025262K context54,656 Toman/M input tokens54,656 Toman/M output tokensMistral: Ministral 3 3B 2512
Accepts- Text
- Image
Creates- Text
ToolsJSONThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
mistralai/ministral-3b-2512Dec 2, 2025131K context37,576 Toman/M input tokens37,576 Toman/M output tokensMistral: Mistral Large 3 2512
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONMistral 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.
mistralai/mistral-large-2512Dec 1, 2025262K context181,048 Toman/M input tokens543,144 Toman/M output tokensMistral: Mistral Embed 2312
Accepts- Text
CreatesMistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications.
mistralai/mistral-embed-2312Oct 31, 20258K context36,039 Toman/M tokensMistral: Codestral Embed 2505
Accepts- Text
CreatesMistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.
mistralai/codestral-embed-2505Oct 30, 20258K context54,058 Toman/M tokensMistral: Voxtral Small 24B 2507
Accepts- Text
- Audio
- File (PDF)
Creates- Text
ToolsJSONVoxtral 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.
mistralai/voxtral-small-24b-2507Oct 30, 202533K context37,576 Toman/M input tokens109,312 Toman/M output tokensMistral: Mistral Medium 3.1
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONMistral 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.
mistralai/mistral-medium-3.1Aug 13, 2025131K context160,552 Toman/M input tokens795,928 Toman/M output tokensMistral: Codestral 2508
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONMistral'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. Blog Post
mistralai/codestral-2508Aug 1, 2025256K context109,312 Toman/M input tokens324,520 Toman/M output tokensMistral: Mistral Small 3.2 24B
Accepts- Text
- Image
Creates- Text
ToolsJSONMistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.
mistralai/mistral-small-3.2-24b-instructJun 20, 2025256K context27,328 Toman/M input tokens75,152 Toman/M output tokensMistral: Mistral Medium 3
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONMistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.
mistralai/mistral-medium-3May 7, 2025131K context160,552 Toman/M input tokens795,928 Toman/M output tokensMistral: Mistral Small 3.1 24B
Accepts- Text
- Image
Creates- Text
ToolsJSONMistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.
mistralai/mistral-small-3.1-24b-instructMar 17, 2025128K context129,808 Toman/M input tokens201,544 Toman/M output tokensMistral: Mistral Saba
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONMistral 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.
mistralai/mistral-sabaFeb 17, 202533K context75,152 Toman/M input tokens218,624 Toman/M output tokensMistral: Mistral Small 3
Accepts- Text
Creates- Text
JSONMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.
mistralai/mistral-small-24b-instruct-2501Jan 30, 202533K context20,496 Toman/M input tokens30,744 Toman/M output tokensMistral: Mistral Large 2407
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONThis 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.
mistralai/mistral-large-2407Nov 19, 2024131K context720,776 Toman/M input tokens2,162,328 Toman/M output tokensMistral: Mistral Nemo
Accepts- Text
Creates- Text
ToolsJSONA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
mistralai/mistral-nemoJul 19, 2024131K context13,664 Toman/M input tokens13,664 Toman/M output tokensMistral: Mixtral 8x22B Instruct
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONMistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size.
mistralai/mixtral-8x22b-instructApr 17, 202466K context720,776 Toman/M input tokens2,162,328 Toman/M output tokensMistral: Mistral Large
Accepts- Text
- File (PDF)
Creates- Text
ToolsJSONThis 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.
mistralai/mistral-largeFeb 26, 2024128K context720,776 Toman/M input tokens2,162,328 Toman/M output tokens
30 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

