Skip to content

Cost to run

Mistral Small 24B

mistral/mistral-small-24b

Family
Mistral Small
Context
32,768 tokens

Mistral Small 24B can be run self-hosted (rent a GPU + run vLLM/TGI) or through a serverless API (pay per token). Live pricing comparisons:

Need to benchmark this model against another? Try the calculator or see where it ranks on the InferenceScore leaderboard.