Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 is a text‑only language model from Mistral AI with a context length of 32,768 tokens. It does not support tool usage or reasoning, is released under open weights, and is priced at $0.05 per input token and $0.08 per output token. The model was released on 2025‑12‑29.

  • structured outputs
  • open-weight

At a glance

providermistralai
releasedDec 29, 2025
context33K
input / M$0.050

Specifications

What the API gives you

Context window
33K tokens
Max output
16K tokens
Input price
$0.050 / 1M tokens
Output price
$0.080 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Oct 31, 2023
Released
Dec 29, 2025

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.

Benchmarks

No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.

Open-weight model on Hugging Face.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.