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.

Base modelAll models on this baseAll models of the providerto the provider

Read also: Mistral API pricing: Mistral Large 4, Large 3, Medium, Small, Codestral and Devstral at every provider

All Mistral models at every provider

Input, $/1M $0.05

Output, $/1M $0.08

Context 32 768

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —