Модели
2 канонические LLM-модели от всех провайдеров
Mistral Large 3256K ctx
Mistral AI's largest open-weight model with 41B active parameters (675B total MoE). State-of-the-art general-purpose multimodal model with 256K context window and powerful agentic capabilities. Released under Apache 2.0.
ЧатГенерация текстаВызов функций
Mistral Small 3.1128K ctx
Mistral AI's Small 3.1 model with 24B parameters offering efficient multimodal capabilities including vision, function calling, and code generation with a large 128K context window.
ЧатГенерация текстаВызов функций