Skip to main content

Bienvenue to Mistral AI Documentation

Mistral AI is a research lab building the best open source models in the world. La Plateforme enables developers and enterprises to build new products and applications, powered by Mistral’s open source and commercial LLMs.

Mistral AI Large Language Models (LLMs)​

We release state-of-the-art generalist models, specialized models, and research models, driving innovation and convenience for our developer community. Our models are state-of-the-art for their multilingual, code generation, maths, and advanced reasoning capabilities.

State-of-the-art generalist models​

  • Mistral Large, our top-tier reasoning model for high-complexity tasks with the lastest version v2 released July 2024
  • Mistral NeMo, our best multilingual open source model released July 2024

Specialized models​

  • Codestral, our cutting-edge language model for coding released May 2024
  • Mistral Embed, our state-of-the-art semantic for extracting representation of text extracts

Research models​

  • Mistral 7b, our first dense model released September 2023
  • Mixtral 8x7b, our first sparse mixture-of-experts released December 2023
  • Mixtral 8x22b, our best open source model to date released April 2024
  • Mathstral 7b, our first math open source model released July 2024
  • Codestral Mamba, our first mamba 2 open source model released July 2024

Learn more about our models here.

Explore the Mistral AI APIs​

The Mistral AI APIs empower LLM applications via:

  • Text generation, enables streaming and provides the ability to display partial model results in real-time
  • Code generation, enpowers code generation tasks, including fill-in-the-middle and code completion
  • Embeddings, useful for RAG where it represents the meaning of text as a list of numbers
  • Function calling, enables Mistral models to connect to external tools
  • Fine-tuning, enables developers to create customized and specilized models
  • JSON mode, enables developers to set the response format to json_object
  • Guardrailing, enables developers to enforce policies at the system level of Mistral models