Mistral Code
Mistral AI
At a glance
- Price per 1M tokens (input)
- $0.30
- Price per 1M tokens (output)
- $0.90
- Context
- 128,000 tokens
- Free access
- yes (see below)
Refreshed daily; data verified September 1, 2026. Published September 1, 2026.
Mistral Code is aimed at developers and technical teams who need a language model that can generate and reason about code while interacting with external tools. Its strength lies in handling programming queries, debugging assistance, and automating workflows that require function execution through tool calling (the ability to invoke predefined functions). The model’s architecture emphasizes precise syntactic output and tight integration with tool interfaces, reflecting Mistral AI’s focus on practical utility over generic generation. It is well suited for environments where reliable code suggestions and controlled external actions are essential.
Specifications & pricing
| Input (per 1M tokens) | $0.30 |
|---|---|
| Output (per 1M tokens) | $0.90 |
| Cache read (per 1M tokens) | $0.03 |
| Context window | 128,000 tokens |
| Max output | 128,000 tokens |
| Capabilities | tool calling |
LiteLLM community dataset (MIT), verified September 1, 2026. Official Mistral AI pricing.
What Mistral Code would cost on your workload — run it through the cost calculator →
Where to try Mistral Code 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 is Mistral Code best suited for?+
It excels at code generation, code review, debugging, and orchestrating tool‑driven workflows where the model can call functions to retrieve data or perform actions.
How do I start using Mistral Code with tool calling?+
Begin by defining the functions you want the model to access, then pass those definitions to the API; the model will request function calls when appropriate, and you handle the responses in your application logic.
How does Mistral Code differ from other Mistral models?+
Unlike the general‑purpose models, Mistral Code is tuned for programming language understanding and includes built‑in support for function calling, whereas the broader models prioritize conversational versatility without specialized code handling.
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.