Models
This guide will explore the performance and cost trade-offs, and discuss how to select the appropriate model for different use cases. We will delve into various factors to consider, offering guidance on choosing the right model for your specific needs.
Featured Models
All Models
Frontier Models
Frontier and Commercial-Grade AI Solutions for Advanced Applications
Magistral Medium 1.2
Our frontier-class multimodal reasoning model.
Mistral Medium 3.1
Our frontier-class multimodal model released August 2025.
Codestral
Our cutting-edge language model for coding released end of July 2025.
Voxtral Mini Transcribe
An efficient audio input model, fine-tuned and optimized for transcription purposes.
Devstral Medium 1.0
An enterprise grade text model, that excels at SWE use cases.
Codestral Embed
Our state-of-the-art semantic for extracting representation of code extracts
OCR
Our OCR service powering our Document AI stack.
Mistral Medium 3
Our frontier-class multimodal model released May 2025.
Mistral Large 2.1
Our top-tier large model for high-complexity tasks with the lastest version released November 2024.
Pixtral Large
Our first frontier-class multimodal model released November 2024.
Mistral Moderation
Our moderation service that enables our users to detect harmful text content.
Ministral 3B
World’s best edge model.
Ministral 8B
Powerful edge model with extremely high performance/price ratio.
Mistral Embed
Our state-of-the-art semantic for extracting representation of code extracts
Open Models
Open-Source AI Models for Community and Research Use
Magistral Small 1.2
Our small multimodal reasoning model.
Voxtral Mini
A mini version of our first audio input model.
Voxtral Small
Our first model with audio input capabilities for instruct use cases.
Devstral Small 1.1
An update to our open source model that excels at SWE use cases.
Mistral Small 3.2
An update to our previous small model, released June 2025.
Pixtral 12B
A 12B model with image understanding capabilities in addition to text.
Mistral Nemo 12B
Our best multilingual open source model released July 2024.
Legacy/Deprecated
Legacy Models
Our model offering is continuously refreshed with newer, better models. As part of this process, we deprecate and retire older models.
| Model | Version | API |
|---|
| Magistral Medium 1.1 ↗ | 25.07 | magistral-medium-2507 |
| Magistral Small 1.1 ↗ | 25.07 | magistral-small-2507 |
| Magistral Medium 1.0 ↗ | 25.06 | magistral-medium-2506 |
| Magistral Small 1.0 ↗ | 25.06 | magistral-small-2506 |
| Devstral Small 1.0 ↗ | 25.05 | devstral-small-2505 |
| Mistral Small 3.1 ↗ | 25.03 | mistral-small-2503 |
| OCR ↗ | 25.03 | mistral-ocr-2503 |
| Mistral Saba ↗ | 25.02 | mistral-saba-2502 |
| Mistral Small 3.0 ↗ | 25.01 | mistral-small-2501 |
| Codestral ↗ | 25.01 | codestral-2501 |
| Mistral Small 2.0 ↗ | 24.09 | mistral-small-2409 |
| Mistral Large 2.0 ↗ | 24.07 | mistral-large-2407 |
| Codestral Mamba 7B ↗ | 0.1 | open-codestral-mamba |
| Mathstral 7B ↗ | 0.1 | |
| Codestral ↗ | 24.05 | codestral-2405 |
| Mistral 7B ↗ | 0.3 | open-mistral-7b |
| Mixtral 8x22B ↗ | 0.1-0.3 | open-mixtral-8x22b |
| Mistral Small 1.0 ↗ | 24.02 | mistral-small-2402 |
| Mistral Large 1.0 ↗ | 24.02 | mistral-large-2402 |
| Mistral Next ↗ | | |
| Mistral Medium 1.0 ↗ | 23.12 | mistral-medium-2312 |
| Mixtral 8x7B ↗ | 0.1 | open-mixtral-8x7b |
| Mistral 7B ↗ | 0.2 | open-mistral-7b |
| Mistral 7B ↗ | 0.1 |