Mistral AI

What is Mistral AI ?

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 API

Mistral AI API provides a seamless way for developers to integrate Mistral’s state-of-the-art models into their applications and production workflows with just a few lines of code. The API is currently available through La Plateforme. You need to activate payments on your account to enable your API keys.

The Mistral AI APIs empower LLM applications via:

• Text generation, enables streaming and provides the ability to display partial model results in real-time
• 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
• 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

Mistral AI Models

Mistral AI offer both open source and commercial models, driving innovation and convenience for our developer community. The models are state-of-the-art for their multilingual, code generation, maths, and advanced reasoning capabilities.

Open Source

• Mistral 7b, the first dense model released September 2023
• Mixtral 8x7b, the first sparse mixture-of-experts released December 2023
• Mixtral 8x22b, the best open source model to date released April 2024

Commercial

• Mistral Small, the cost-efficient reasoning model for low-latency workloads
• Mistral Medium, useful for intermediate tasks that require moderate reasoning; please note that this model will be deprecated in the coming months
• Mistral Large, the top-tier reasoning model for high-complexity tasks
• Mistral Embeddings, the state-of-the-art semantic for extracting representation of text extracts