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.

Базовая модельВсе модели этой базовойВсе модели провайдерак провайдеру

Читайте также: Цены на API Mistral: Mistral Large 4, Large 3, Medium, Small, Codestral и Devstral у всех провайдеров

Все модели Mistral у всех провайдеров

Вход, $/1M $0.05

Выход, $/1M $0.08

Контекст 32 768

Принимает —

Последняя проверка 04.11.2026 12:00:14 UTC

Источник —