Mistral API

Access Mistral AI’s frontier models via a high-performance REST API for RAG, code generation, and multilingual reasoning.

Mistral API delivers direct access to a tiered model family (including Mistral Large 2, Codestral, and Mistral NeMo) optimized for low-latency inference and high throughput. Developers use the platform to integrate 128k context windows and native function calling into production workflows. The infrastructure supports flexible deployment through La Plateforme or major cloud partners (Azure, AWS, and GCP) while maintaining strict data privacy standards (SOC2 compliance). With competitive pricing based on million-token increments, it provides a cost-effective alternative for scaling complex LLM applications.

https://docs.mistral.ai/