# Models Overview

| Model | API name | Status | Context | Summary |
| --- | --- | --- | --- | --- |
| [Z.ai GLM 5.3 Flash](/models/zai-glm-5-3-flash) | `zai-glm-5-3-flash` | GA | 1M | A third-party multimodal model from Z.ai with a 1M-token context window, optimized for agentic workflows and visual coding. |
| [Z.ai GLM 5.3](/models/zai-glm-5-3) | `zai-glm-5-3` | GA | 1M | A third-party open weight text model from Z.ai with a 1M-token context window. |
| [Shieldstral 1.0](/models/shieldstral-1-0) |  | Public Preview | 32k | Compact multimodal moderation model for text and image safety classification. |
| [Timestral 1.0 209M](/models/timestral-1-0-209m) |  | Public Preview | 32K | A time series foundation model for zero-shot forecasting with covariate support and probabilistic outputs. |
| [Timestral 1.0 123M](/models/timestral-1-0-123m) |  | Public Preview | 32K | A time series foundation model for zero-shot forecasting with covariate support and probabilistic outputs. |
| [Timestral 1.0 28M](/models/timestral-1-0-28m) |  | Public Preview | 32K | A time series foundation model for zero-shot forecasting with covariate support and probabilistic outputs. |
| [Timestral 1.0 5M](/models/timestral-1-0-5m) |  | Public Preview | 32K | A time series foundation model for zero-shot forecasting with covariate support and probabilistic outputs. |
| [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) | `mistral-medium-3-5` | GA | 256k | Our frontier-class multimodal model optimized for agentic and coding use cases. |
| [Voxtral TTS](/models/voxtral-tts-26-03) | `voxtral-mini-tts-2603` | GA |  | State-of-the-art TTS with zero-shot voice cloning and multilingual support. |
| [Voxtral Mini Transcribe 3](/models/voxtral-mini-transcribe-3-0) | `voxtral-mini-transcribe-3-0` | Public Preview | 32k | Strong transcription and diarization at a competitive price point. |
| [Voxtral Small Transcribe 3](/models/voxtral-small-transcribe-3-0) | `voxtral-small-transcribe-3-0` | Public Preview | 32k | Flagship transcription and diarization model with SOTA accuracy. |
| [Voxtral Mini Transcribe Realtime 3](/models/voxtral-mini-transcribe-realtime-3-0) | `voxtral-mini-transcribe-realtime-3-0` | Public Preview | -- | Realtime transcription model for agentic use-cases with configurable latency and turn detection. |
| [Voxtral TTS 3](/models/voxtral-mini-tts-3-0) | `voxtral-mini-tts-3-0` | Public Preview |  | State-of-the-art TTS with zero-shot and professional voice cloning, 9 languages, and streaming. |
| [Mistral Small 4](/models/mistral-small-4-0-26-03) | `mistral-small-2603` | GA | 256k | Hybrid model unifying instruct, reasoning, and coding in a single efficient model. |
| [Mistral Large 4](/models/mistral-large-4-0) | `mistral-large-4` | Public Preview | 1M | A state-of-the-art, open-weight, general-purpose multimodal model. |
| [Mistral Large 3](/models/mistral-large-3-25-12) | `mistral-large-2512` | GA | 256k | A state-of-the-art, open-weight, general-purpose multimodal model. |
| [OCR 4.1](/models/ocr-4-1) | `mistral-ocr-4-1` | GA |  | Our latest OCR service with paragraph-level bounding boxes, structural block labels, and block-level confidence scores. |
| [OCR 3](/models/ocr-3-25-12) | `mistral-ocr-2512` | GA |  | Our OCR service powering our Document AI stack. OCR 4 is available as the newer model. OCR 3 remains available for existing integrations and production workloads. |
| [Voxtral Mini Transcribe 2](/models/voxtral-mini-transcribe-26-02) | `voxtral-mini-2602` | GA | -- | An efficient audio input model, pre-trained and optimized for transcription purposes. |
| [Voxtral Mini Transcribe Realtime](/models/voxtral-mini-transcribe-realtime-26-02) | `voxtral-mini-transcribe-realtime-2602` | GA | -- | An efficient audio input model, pre-trained and optimized for live transcription purposes. |
| [Codestral](/models/codestral-25-08) | `codestral-2508` | GA | 128k | Our cutting-edge language model for code completion released end of July 2025. |
| [Codestral Embed](/models/codestral-embed-25-05) | `codestral-embed-2505` | GA | 8k | Our state-of-the-art semantic for extracting representation of code extracts |
| [Ministral 3 14B](/models/ministral-3-14b-25-12) | `ministral-14b-2512` | GA | 256k | A powerful model offering best-in-class text and vision capabilities.  |
| [Ministral 3 8B](/models/ministral-3-8b-25-12) | `ministral-8b-2512` | GA | 256k | A powerful and efficient model offering best-in-class text and vision capabilities.  |
| [Ministral 3 3B](/models/ministral-3-3b-25-12) | `ministral-3b-2512` | GA | 256k | A tiny and efficient model offering best-in-class text and vision capabilities.  |
| [Voxtral Small](/models/voxtral-small-25-07) | `voxtral-small-2507` | GA | 32k | Our first model with audio input capabilities for instruct use cases. |
| [Mistral Moderation 2](/models/mistral-moderation-26-03) | `mistral-moderation-2603` | GA | 128k | Our latest moderation model with 128k context window and jailbreaking detection. |
| [Mistral Embed](/models/mistral-embed-23-12) | `mistral-embed-2312` | GA | 8k | A general-purpose text embedding model for retrieval and similarity search. |

## Deprecated and retired models

A deprecated model still answers requests until its retirement date. A retired model no longer does: use its replacement.

| Model | API name | Status | Context | Summary | Deprecation | Retirement | Replacement |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Z.ai GLM 5.2](/models/zai-glm-5-2) | `zai-glm-5-2` | Deprecated | 1M | A third-party open weight text model from Z.ai with a 1M-token context window. | 2026-09-29 | 2026-10-31 | [Z.ai GLM 5.3](/models/zai-glm-5-3) |
| [Leanstral 1.5](/models/leanstral-1-5) | `labs-leanstral-1-5` | Deprecated | 256k | Updated code agent for Lean 4 formal proof engineering and automated theorem proving. | 2026-09-29 | 2026-09-30 |  |
| [Leanstral](/models/leanstral-26-03) | `labs-leanstral-2603` | Retired | 256k | Open-source code agent for Lean 4 formal proof engineering. | 2026-05-22 | 2026-06-30 | [Leanstral 1.5](/models/leanstral-1-5) |
| [Mistral Medium 3.1](/models/mistral-medium-3-1-25-08) | `mistral-medium-2508` | Deprecated | 128k | Our frontier-class multimodal model released August 2025. | 2026-05-22 | 2026-08-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mistral Small 3.2](/models/mistral-small-3-2-25-06) | `mistral-small-2506` | Deprecated | 128k | An update to our previous small model, released June 2025. | 2026-04-30 | 2026-07-31 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [OCR 4.0](/models/ocr-4-0) | `mistral-ocr-4-0` | Deprecated |  | Our latest OCR service with paragraph-level bounding boxes and structural block labels. | 2026-09-29 | 2026-09-30 | [OCR 4.1](/models/ocr-4-1) |
| [Voxtral Mini Transcribe](/models/voxtral-mini-transcribe-25-07) | `voxtral-mini-2507` | Deprecated | 32k | An efficient audio input model, pre-trained and optimized for transcription purposes. | 2026-02-27 | 2026-05-31 | [Voxtral Mini Transcribe 2](/models/voxtral-mini-transcribe-26-02) |
| [Devstral 2](/models/devstral-2-25-12) | `devstral-2512` | Deprecated | 256k | Our frontier code agents model for solving software engineering tasks. | 2026-05-22 | 2026-07-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Magistral Medium 1.1](/models/magistral-medium-1-1-25-07) | `magistral-medium-2507` | Retired | 40k | Our frontier-class reasoning model released July 2025. | 2025-10-31 | 2025-11-30 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mistral Small Creative](/models/mistral-small-creative-25-12) | `labs-mistral-small-creative` | Deprecated | 32k | A specialized model designed for creative writing and dynamic character interaction. | 2026-03-31 | 2026-04-30 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |
| [Devstral Small 2](/models/devstral-small-2-25-12) | `labs-devstral-small-2512` | Deprecated | 256k | Model that excels at using tools to explore codebases, editing multiple files and power software engineering agents. | 2026-02-27 | 2026-03-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Magistral Medium 1.2](/models/magistral-medium-1-2-25-09) | `magistral-medium-2509` | Deprecated | 128k | Our frontier-class multimodal reasoning model. | 2026-05-22 | 2026-07-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Magistral Small 1.2](/models/magistral-small-1-2-25-09) | `magistral-small-2509` | Deprecated | 128k | Our small multimodal reasoning model. | April 30, 2026 | July 31, 2026 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Magistral Small 1.1](/models/magistral-small-1-1-25-07) | `magistral-small-2507` | Retired | 40k | Our small reasoning model released July 2025. | 2025-10-31 | 2025-11-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Voxtral Mini](/models/voxtral-mini-25-07) | `voxtral-mini-2507` | Deprecated | 32k | A mini version of our first audio input model. | 2026-02-27 | 2026-05-31 | [Voxtral Mini Transcribe 2](/models/voxtral-mini-transcribe-26-02) |
| [Devstral Medium 1.0](/models/devstral-medium-1-0-25-07) | `devstral-medium-2507` | Deprecated | 128k | An enterprise grade text model, that excels at SWE use cases. | 2026-02-27 | 2026-05-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Devstral Small 1.1](/models/devstral-small-1-1-25-07) | `devstral-small-2507` | Deprecated | 128k | An update to our open source model that excels at SWE use cases. | 2026-02-27 | 2026-05-31 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Magistral Medium 1.0](/models/magistral-medium-1-0-25-06) | `magistral-medium-2506` | Retired | 40k | Our first frontier-class reasoning model released June 2025 | 2025-10-31 | 2025-11-30 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Magistral Small 1.0](/models/magistral-small-1-0-25-06) | `magistral-small-2506` | Retired | 40k | Our first small reasoning model released June 2025. | 2025-10-31 | 2025-11-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [OCR 2](/models/ocr-2-25-05) | `mistral-ocr-2505` | Deprecated |  | Our OCR service powering our Document AI stack. | 2026-02-27 | 2026-05-31 | [OCR 4.1](/models/ocr-4-1) |
| [Devstral Small 1.0](/models/devstral-small-1-0-25-05) | `devstral-small-2505` | Retired | 128k | A 24B text model, open source model that excels at SWE use cases. | 2025-10-31 | 2025-11-30 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mistral Medium 3](/models/mistral-medium-3-25-05) | `mistral-medium-2505` | Deprecated | 128k | Our frontier-class multimodal model released May 2025. | 2026-05-22 | 2026-08-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mistral Small 3.1](/models/mistral-small-3-1-25-03) | `mistral-small-2503` | Retired | 128k | A new leader in the small models category with image understanding capabilities. | 2025-11-06 | 2025-11-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [OCR](/models/ocr-25-03) | `mistral-ocr-2503` | Deprecated |  | Our first OCR optimized model. | 2025-12-02 | 2025-12-31 | [OCR 4.1](/models/ocr-4-1) |
| [Mistral Saba](/models/mistral-saba-25-02) | `mistral-saba-2502` | Retired | 32k | A finetuned Small model trained on meticulously curated datasets. | 2025-06-10 | 2025-09-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Mistral Small 3.0](/models/mistral-small-3-0-25-01) | `mistral-small-2501` | Retired | 32k | A small efficient and powerfull 24B open model for personal or commercial use. | 2025-11-06 | 2025-11-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Codestral](/models/codestral-25-01) | `codestral-2501` | Retired | 128k | Our cutting-edge language model for coding. | 2025-11-06 | 2025-11-30 | [Codestral](/models/codestral-25-08) |
| [Mistral Large 2.1](/models/mistral-large-2-1-24-11) | `mistral-large-2411` | Deprecated | 128k | Our top-tier large model for high-complexity tasks with the lastest version released November 2024. | 2026-02-27 | 2026-05-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Pixtral Large](/models/pixtral-large-24-11) | `pixtral-large-2411` | Deprecated | 128k | Our first frontier-class multimodal model released November 2024. | 2026-02-27 | 2026-05-31 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mistral Moderation](/models/mistral-moderation-24-11) | `mistral-moderation-2411` | Deprecated | 8k | Our moderation service that enables our users to detect harmful text content. | 2026-03-31 | 2026-06-30 | [Mistral Moderation 2](/models/mistral-moderation-26-03) |
| [Ministral 3B](/models/ministral-3b-24-1) | `ministral-3b-2410` | Deprecated | 128k | World’s best edge model. | 2025-12-02 | 2025-12-31 | [Ministral 3 3B](/models/ministral-3-3b-25-12) |
| [Ministral 8B](/models/ministral-8b-24-1) | `ministral-8b-2410` | Deprecated | 128k | Powerful edge model with extremely high performance/price ratio. | 2025-12-02 | 2025-12-31 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |
| [Mistral Small 2.0](/models/mistral-small-2-0-24-09) | `mistral-small-2409` | Retired | 32k | An update to our efficient small model with open weights under an MRL license. | 2025-11-06 | 2025-11-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Pixtral 12B](/models/pixtral-12b-24-09) | `pixtral-12b-2409` | Deprecated | 128k | A 12B model with image understanding capabilities in addition to text. | 2025-12-02 | 2025-12-31 | [Ministral 3 14B](/models/ministral-3-14b-25-12) |
| [Mistral Large 2.0](/models/mistral-large-2-0-24-07) | `mistral-large-2407` | Retired | 128k | A powerfull model with open weights under a MRL license. | 2024-11-30 | 2025-03-30 | [Mistral Large 3](/models/mistral-large-3-25-12) |
| [Mistral Nemo 12B](/models/mistral-nemo-12b-24-07) | `open-mistral-nemo-2407` | Deprecated | 128k | Our best multilingual open source model released July 2024. | 2026-05-22 | 2026-07-31 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |
| [Codestral Mamba 7B](/models/codestral-mamba-7b-0-1) | `open-codestral-mamba` | Retired | 256k | A coding dedicated model using a mamba 2 architecture for research purposes. | 2025-06-06 | 2025-06-06 | [Codestral](/models/codestral-25-08) |
| [Mathstral 7B](/models/mathstral-7b-0-1) |  | Retired | 32k | A math dedicated model for research purposes. |  |  | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Codestral](/models/codestral-24-05) | `codestral-2405` | Retired | 32k | Our first cutting-edge language model for coding and FIM. | 2024-12-02 | 2025-06-16 | [Codestral](/models/codestral-25-08) |
| [Mistral 7B](/models/mistral-7b-0-3) | `open-mistral-7b` | Retired | 32k | A minor update to our first open model. | 2024-11-30 | 2025-03-30 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |
| [Mixtral 8x22B](/models/mixtral-8x22b-0-1-0-3) | `open-mixtral-8x22b` | Retired | 64k | A large open MoE model competing with much larger dense models. | 2024-11-30 | 2025-03-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Mistral Small 1.0](/models/mistral-small-1-0-24-02) | `mistral-small-2402` | Retired | 32k | An enterprise grade small model for efficiency. | 2024-11-30 | 2025-06-16 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Mistral Large 1.0](/models/mistral-large-1-0-24-02) | `mistral-large-2402` | Retired | 32k | Our first and larger SOTA model for enterprise use cases. | 2024-11-30 | 2025-06-16 | [Mistral Large 3](/models/mistral-large-3-25-12) |
| [Mistral Next](/models/mistral-next) |  | Retired |  | A prototype model, designed to be brief and concise. |  |  | [Mistral Large 3](/models/mistral-large-3-25-12) |
| [Mistral Medium 1.0](/models/mistral-medium-1-0-23-12) | `mistral-medium-2312` | Retired | 32k | Our first SOTA enterprise grade model. | 2024-11-30 | 2025-06-16 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) |
| [Mixtral 8x7B](/models/mixtral-8x7b-0-1) | `open-mixtral-8x7b` | Retired | 32k | Our first open MoE model, SOTA competing against models up to 2 to 3x larger. | 2024-11-30 | 2025-03-30 | [Mistral Small 4](/models/mistral-small-4-0-26-03) |
| [Mistral 7B](/models/mistral-7b-0-2) | `open-mistral-7b` | Retired | 32k | An update to our first open model with better context. | 2024-11-30 | 2025-03-30 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |
| [Mistral 7B](/models/mistral-7b-0-1) |  | Retired | 8k | Our very first open model, SOTA competing against models up to 2 to 3x larger. | 2024-11-30 | 2025-03-30 | [Ministral 3 8B](/models/ministral-3-8b-25-12) |