Voxtral Small
Mistral AI
At a glance
- Price per 1M tokens (input)
- $0.10
- Price per 1M tokens (output)
- $0.40
- Context
- 32,768 tokens
- Free access
- yes (see below)
Refreshed daily; data verified August 30, 2026. Published August 30, 2026.
Voxtral Small is aimed at developers and business teams that need a lightweight reasoning engine capable of invoking external functions. It excels at tasks where structured data retrieval, calculation, or interaction with APIs is required, such as ticket routing, inventory checks, or dynamic report generation. Mistral AI’s approach focuses on a clear separation between language understanding and tool execution, allowing the model to hand off specific operations to reliable code while preserving conversational flow. The model is designed to run efficiently on modest hardware, making it suitable for on‑premise deployments.
Specifications & pricing
| Input (per 1M tokens) | $0.10 |
|---|---|
| Output (per 1M tokens) | $0.40 |
| Context window | 32,768 tokens |
| Max output | 32,768 tokens |
| Capabilities | tool calling |
LiteLLM community dataset (MIT), verified August 30, 2026. Official Mistral AI pricing.
What Voxtral Small would cost on your workload — run it through the cost calculator →
Where to try Voxtral 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
What kinds of applications benefit most from tool calling?+
Any workflow that requires the model to fetch real‑time information, perform calculations, or trigger external services gains from tool calling, including customer support bots, data validation pipelines, and automated scheduling assistants.
How do I integrate Voxtral Small into my existing system?+
Integration follows the standard API pattern: send a prompt, receive a response that includes a tool call specification, execute the indicated function, and feed the result back to the model for continuation. Documentation provides sample code for common programming environments.
How does Voxtral Small differ from larger models in the Mistral family?+
Voxtral Small trades raw language breadth for a tighter footprint and faster inference, while still preserving the full tool‑calling capability. Larger siblings retain broader knowledge and generate longer, more nuanced prose, whereas Voxtral Small focuses on concise, task‑oriented interactions with minimal resource demands.
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.