Skip to main content
mistral.health

Learn

Plain-English guides to Mistral AI, La Plateforme, and the broader open-model ecosystem. No fluff, no affiliate spam.

Quick answer: mistral.health Learn provides developer guides, API architecture tutorials, pricing comparisons, and endpoint reference documentation for Mistral AI, La Plateforme, Codestral, and compatible open-weight LLMs.

Mistral basics

La Plateforme pricing in 2026: what you actually pay

Mistral's pricing is per million tokens, split across input and output, with real discounts on batch and embed. Here's how to model it.

Read

Compare platforms

Mistral Large vs Small: which model to pick in 2026

Both models sit on La Plateforme. One is a frontier flagship; the other is 5–10× cheaper. Here's when each actually wins.

Read

Developer guides

Function calling with Mistral: the practical guide

Function calling on Mistral is OpenAI-compatible in shape, but with stricter JSON-schema validation. Here's the working pattern.

Read

Codestral Guide: Capabilities, IDE Use & Benchmarks

Codestral is the model to reach for on autocomplete, refactor, and tight code generation. It's not the right choice for full agentic coding.

Read

BioMistral: the medical LLM built on Mistral 7B

BioMistral fine-tunes Mistral 7B on PubMed-scale biomedical text. Here's what the benchmarks say, how it's licensed, and how to deploy it safely.

Read

Reference

Mistral API glossary: 25 terms every developer should know

A focused glossary of the terms that show up in the Mistral docs, dashboards, and error messages — plus a few from the surrounding LLM ecosystem.

Read

FAQ

Where can I find Mistral AI developer tutorials?
The mistral.health Learn hub offers comprehensive tutorials on function calling, Codestral code generation, token pricing optimization, and OpenAI SDK compatibility for Mistral AI.
Is Mistral AI compatible with the OpenAI API format?
Yes, Mistral API endpoints follow OpenAI-compatible chat completion and embedding schemas, allowing developers to switch providers by changing the base URL and authorization header.
How do I choose between Mistral Large and Mistral Small?
Use Mistral Small for high-throughput, low-latency tasks like classification and summarization, and Mistral Large for complex multi-step reasoning, coding, and structured JSON output.