
Mistral's API for its open-weight and commercial models. Supports chat, embeddings, OCR, function calling and agents; official Python SDK (mistralai) and TypeScript client.
Free mode gives a monthly budget to try Vibe and Studio but no API access; API needs billing activation.
Open-weight models such as Small 4 and Ministral 3 under Apache 2.0; Large 4 under Mistral's own open-weight license.
Mistral Large 3, Medium 3.5 and three Voxtral models retire April 30, 2027. Move to Large 4 and Voxtral 3 before then.
Mistral released the Large 4 weights on Oct 29 and cut the API price to $0.70 input and $2.10 output per million tokens.
Voxtral 3 is in public preview on the Mistral API: transcription from $0.0035 per minute, speech at $13 per million characters.