Magistral Small 1.2
API ID magistral-small-2509
Magistral Small 1.2 was a Mistral model, released September 2025. It had a 128,000-token context window. It took image and PDF input and supported function calling and reasoning.
Our small multimodal reasoning model update of September 2025.
- Status
- Retired
- Released
- September 2025
- Shutdown
- Jul 31, 2026
- Replacement
- Mistral Small 4mistral-small-2603
magistral-small-2509 stopped serving on July 31, 2026. Recommended replacement: mistral-small-2603.
How to migrate to Mistral Small 4
Benchmarks
Scores as each source published themComparing with Magistral Small 1.0, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Epoch AI
| Benchmark | Magistral Small 1.2 | Magistral Small 1.0 | Change | Setting | Run | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | 47.6% | 56.1% | −8.5 pts | Aug 30, 2026 | source | |
| OTIS Mock AIME 2024-2025 | 28.1% | 30.0% | −1.9 pts | Aug 30, 2026 | source |
Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
On cloud platforms
All platform dates| Platform | Platform ID | State | Shutdown | Time left | Replacement | Source |
|---|---|---|---|---|---|---|
| Amazon Bedrock | mistral.magistral-small-2509 | Active | none announced | — | source |
Read daily from each platform's own pages. The shutdown date and countdown on this page use Mistral's own date.
Aliases pointing here: magistral-small-latest (in place when tracking began (October 6, 2026))
Features
Compare models| Feature | Value | Since | Source |
|---|---|---|---|
| Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result. | Supported | in place when tracking began (October 6, 2026) | source |
| Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests. | Supported | in place when tracking began (October 6, 2026) | source |
| Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read. | Supported | in place when tracking began (October 6, 2026) | source |
| PDF inputPDF files can go in the prompt directly, without converting them to text first. | Supported | in place when tracking began (October 6, 2026) | source |
| Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time. | Supported | in place when tracking began (October 6, 2026) | source |
| Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word. | 128,000 tokens | in place when tracking began (October 6, 2026) | source |
Not published by Mistral: Structured outputs, Prompt caching, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 5, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 5, 2026 | Input | $0.50 |
| Oct 5, 2026 | Output | $1.50 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Price $/1M | In effect |
|---|---|---|
| Standard | ||
| input | $0.50 | |
| output | $1.50 | |
Changelog
Changes we detected on Mistral's pagesNo changes recorded yet.
Last checked · Sources: Mistral models