Model prices / Mistral AI / Mistral Small (latest)
Mistral Small (latest)Open weights
Mistral AI · released 2026-03-16
The official API price of Mistral Small (latest) is $0.15 per 1M input tokens and $0.6 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 256K output tokens per request. 5 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| MistralOfficialmistral-small-latest | $0.15 | $0.6 | $0.015 | Official | Official docs |
EEden AImistral/ | $0.15 | $0.6 | $0.015 | Official docs | |
MMerge Gatewaymistral/ | $0.15 | $0.6 | — | Official docs | |
TTempr Gatewaymistral/ | $0.15 | $0.6 | $0.015 | Official docs | |
 Vercel AI Gatewaymistral/ | $0.15 | $0.6 | $0.015 | Official docs | |
EEden AImistral/ | $0.165 | $0.66 | $0.0165 | 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
- 262K
- Max output
- 256K
- Input
- Text, Image, PDF
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-06
- Open weights
- Yes
- Released
- 2026-03-16
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.