TPSTokens Per Second

Mistral Small 3

Mistral AI🇫🇷 France
active
Compare with other models →
Context window33K tokens
Input / 1M tokens$0.05
Output / 1M tokens$0.08

Version History

24b-instruct-2501major

Mistral Small 3 introduces a new 24B-parameter model optimized for inference speed, delivering 3x faster performance than 70B models while maintaining competitive accuracy at 81% MMLU.