Mistral Small 3 · deepinfra

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Leia também: Preços da API da Mistral: Mistral Large 4, Large 3, Medium, Small, Codestral e Devstral em todos os provedores

Todos os modelos Mistral em todos os provedores

Entrada, $/1M $0.05

Saída, $/1M $0.08

Contexto 32 768

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —