Model prices / Mistral AI / Mistral Small 3.1 24B
Mistral Small 3.1 24BOpen weights
Mistral AI · released 2025-03-17
No price from the maker itself is on record for Mistral Small 3.1 24B. The lowest of 5 providers is NanoGPT: $0.1 per 1M input tokens and $0.3 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 102K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestmistralai/ | $0.1 | $0.3 | $0.05 | Lowest | Official docs |
EEden AIcloudflare/ | $0.351 | $0.555 | — | Official docs | |
KKilo Gatewaymistralai/ | $0.351 | $0.555 | — | Official docs | |
 OpenRoutermistralai/ | $0.351 | $0.555 | — | Official docs | |
 AI/ML APImistralai/ | $0.371358 | $0.58719 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Efficient Mistral model for fast chat, extraction, and production assistants
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 102K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2023-10-31
- Open weights
- Yes
- Released
- 2025-03-17
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.