Mistral Small 3
Mistral
mistralai/mistral-small-24b-instruct-2501Mistral Small 3 (24B, January 2025) is a dense open-weight model from Mistral AI tuned for low-latency chat, coding, and instruction-following. It is designed to deliver strong performance at a fraction of the cost of larger models.
Cost rate
0.1x
Context
33K
Released
Jan 30, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Mathematical
#262 · top 71%
Medicine & Healthcare
#269 · top 75%
Software & IT Services
#278 · top 71%
Life, Physical, & Social Science
#283 · top 72%
Performance
Median latency and throughput measured across recent requests.
Throughput142 tok/s
Latency