Magistral Small
Mistral AI
At a glance
- Price per 1M tokens (input)
- $0.50
- Price per 1M tokens (output)
- $1.50
- Context
- 40,000 tokens
- Free access
- yes (see below)
Refreshed daily; data verified August 15, 2026. Published August 12, 2026.
Magistral Small is aimed at developers and business teams that need a lightweight model capable of handling routine language tasks while also supporting tool calling (function calling), which lets the model invoke external functions for up‑to‑date information or specialized operations. It performs well on summarisation, classification, and simple data extraction, and its step‑by‑step reasoning helps produce transparent intermediate steps for debugging. Mistral AI’s approach combines a compact architecture with explicit support for function calls, offering a predictable balance between speed and reasoning depth without relying on massive parameter counts.
Specifications & pricing
| Input (per 1M tokens) | $0.50 |
|---|---|
| Output (per 1M tokens) | $1.50 |
| Context window | 40,000 tokens |
| Max output | 40,000 tokens |
| Capabilities | tool calling, reasoning |
LiteLLM community dataset (MIT), verified August 15, 2026. Official Mistral AI pricing.
What Magistral Small would cost on your workload — run it through the cost calculator →
Where to try Magistral Small for free
- Mistral AI offers a free chat — Le Chat (free plan). A vendor's free chat may run a different model from the same family — the exact model is not guaranteed.
Frequently asked questions
Which business use cases benefit most from this model?+
Typical use cases include generating concise summaries of internal documents, categorising support tickets, extracting key fields from forms, and orchestrating external APIs through tool calling to enrich responses with real‑time data.
How do I activate tool calling when using the model?+
Tool calling is enabled by defining a set of functions in the request payload; the model will then suggest a function name and arguments whenever it determines that an external operation would improve the answer, and the client executes the call and returns the result.
In what ways does Magistral Small differ from its larger siblings?+
Compared with larger models, this version trades raw language breadth for faster inference and lower resource consumption, while still preserving the ability to perform step‑by‑step reasoning and to call tools, making it suitable for latency‑sensitive applications.
What limitations should I be aware of before deploying it?+
The model may struggle with highly nuanced or domain‑specific queries that require deep expertise, and its reasoning depth is modest, so complex multi‑turn dialogues might need fallback to a more capable model for final verification.
Compare with others
Org chart: how to move your company onto AI
A practical map: which company roles and processes AI agents can take over, where to start, and in what order to roll it out.