Mistral AI (BYOK)BYOK

Codestral 2508 is Mistral's coding model, released at the end of July 2025. It specializes in low-latency, high-frequency tasks such as fill-in-the-middle, code correction and test generation. Context is 256,000 tokens, with function calling.

Ministral 3 14B 2512 is the largest model in the Ministral 3 family, with performance comparable to Mistral Small 3.2 24B. It takes text and image input, supports function calling and has a 262,144-token context window.

Ministral 3 3B 2512 is the smallest model in the Ministral 3 family, a small, efficient language model with vision. It takes text and image input, supports function calling and has a 131,072-token context window.

Ministral 3 8B 2512 is a balanced model in the Ministral 3 family, a small, efficient language model with vision. It takes text and image input, supports function calling and has a 262,144-token context window.

Mistral Large 4 is Mistral AI's open-weight Mixture-of-Experts model with about 1 trillion parameters and a 1M-token context. It takes text and image input and supports tool use, structured output and Low, Medium or High reasoning effort.

Mistral Medium 3.5 128B is an open-weight 128B-parameter Mixture-of-Experts model balancing capability and efficiency. It is strong at reasoning, coding and multilingual tasks, and supports function calling with text input and output.

Mistral Medium 3 is a high-performance enterprise-grade language model. It takes text, image and file input, returns text, supports function calling and has a 131,072-token context window.

Mistral Small 3.1 24B Instruct builds on Mistral Small 3 (2501) and adds vision understanding. It handles long context up to 128k tokens, has 24 billion parameters, takes text and image input and supports function calling.

Mistral Small 4 is a hybrid instruct-and-reasoning mixture-of-experts model with a 256k context window. It takes text and image input under Apache 2.0. It folds Mistral's separate Instruct, reasoning and coding lines into one model.