Devstral Small
Mistral AI
At a glance
- Price per 1M tokens (input)
- $0.10
- Price per 1M tokens (output)
- $0.30
- Context
- 256,000 tokens
- Free access
- yes (see below)
Refreshed daily; data verified August 15, 2026. Published August 12, 2026.
Devstral Small by Mistral AI is designed for developers and small teams that need a lightweight language model with integrated tool calling capability. It is well suited for automating routine queries, generating code snippets, and orchestrating external APIs within a conversational flow. Mistral’s approach emphasizes modular prompting and open‑source friendliness, allowing users to customize the model’s behavior without relying on proprietary pipelines. The model’s tool calling lets it invoke defined functions, turning natural language requests into precise programmatic actions. It offers a balance of performance and resource efficiency for applications that require quick turn‑around without large infrastructure.
Specifications & pricing
| Input (per 1M tokens) | $0.10 |
|---|---|
| Output (per 1M tokens) | $0.30 |
| Context window | 256,000 tokens |
| Max output | 256,000 tokens |
| Capabilities | tool calling |
LiteLLM community dataset (MIT), verified August 15, 2026. Official Mistral AI pricing.
What Devstral Small would cost on your workload — run it through the cost calculator →
Where to try Devstral 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 types of tasks can Devstral Small handle effectively?+
It handles code assistance, data look‑ups, simple summarisation, and any workflow that can be expressed through defined functions.
How do I start using the model’s tool calling feature?+
First register the functions you want the model to access, then pass the function schema along with your prompt; the model will return a structured call that your application can execute.
How does Devstral Small differ from larger models in the Devstral line?+
It trades raw language depth for lower compute demand, making it faster on modest hardware, while still supporting tool calling; larger siblings retain broader knowledge and longer context.
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.