Mistral AI
Models published by Mistral AI, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
A 128B parameter Mixture-of-Experts model balancing capability and efficiency, with strong performance on reasoning, coding, and multilingual tasks. Served via NVIDIA NIM with fast inference and optimized latency.
Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.
Mistral Small 3.2 is a 24B instruction model with a 131k context window, improved instruction following and function calling over Mistral Small 3.1, and the same Apache 2.0 license.
Mistral Small 4 is a hybrid instruct-and-reasoning mixture-of-experts model on a 256k context window. Apache 2.0, and it takes image input as well as text. It folds Mistral's separate Instruct, reasoning and coding lines into one model, at $0.15 per 1M input and $0.60 per 1M output — roughly a tenth of Mistral Medium 3.5.