Magistral Small 2506
Summary
Magistral Small 2506 is a proprietary language model from Mistral AI, released on 25 Sept 2025. It accepts text and generates text, with a 33K-token context window and up to 33K output tokens per response.
Mistral reasoning model for transparent analysis, math, and complex decisions
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Mistral AI |
|---|---|
| Release date | 25 Sept 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 33K (32,768 tokens) [models.dev] |
| Max output | 33K tokens [models.dev] |
| Knowledge cutoff | Jan 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | No [models.dev] |
Magistral Small 2506 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| NVIDIA NIM mistralai/magistral-small-2506 | Free | Free | – | 33K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Magistral Small 2506?
Magistral Small 2506 has a context window of 32,768 tokens (33K) and can generate up to 32,768 tokens in a single response, according to models.dev.
Is Magistral Small 2506 open source?
No. Magistral Small 2506 is a proprietary model; Mistral AI has not released its weights. It is available through APIs including NVIDIA NIM.
When was Magistral Small 2506 released?
Mistral AI released Magistral Small 2506 on 25 Sept 2025, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.