Mistral 模型

Mistral's frontier-class multimodal model optimized for agentic and coding use cases.

Mistral Large 4 is Mistral AI's open-weight, natively multimodal model, available in public preview with 1.05 trillion total parameters and 49 billion active parameters.

Mistral Small currently runs Mistral Small 4, a multimodal model combining instruction following, reasoning, and coding with a 262,144-token context window.

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Mistral Large 3 2512 is Mistral’s most capable model to date.

General-purpose text embedding model for semantic search, similarity, clustering, and RAG workflows.

A more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.

A compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.

Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.

Code embedding model that can embed code databases and repositories to power coding assistants.

Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.