# Magistral Small 2506

> 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.

Source page: https://www.aimodel.directory/models/magistral-small-2506
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Mistral AI
- **Release date:** 25 Sept 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Max output:** 33K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/magistral-small-2506.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | 33K |

## FAQ

### 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.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Magistral Small 2506", https://www.aimodel.directory/models/magistral-small-2506