Magistral Small 2506DeprecatedOpen weights
Mistral AI · released 2025-06-10
No price from the maker itself is on record for Magistral Small 2506. The lowest of 2 providers is IO.NET: $0.5 per 1M input tokens and $1.5 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 32.8K output tokens per request. This model is marked as deprecated.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 IO.NETLowestDeprecatedmistralai/ | $0.5 | $1.5 | $0.25 | LowestDeprecated | Official docs |
 NvidiaDeprecatedmistralai/ | $0 | $0 | — | Deprecated | 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
Mistral reasoning model for transparent analysis, math, and complex decisions
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 32.8K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Knowledge cutoff
- 2025-01
- Open weights
- Yes
- Released
- 2025-06-10
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.