Mistral Large 4 is now live in Command Code. It's a mixture-of-experts model with 1T total parameters, 49B of which are active per token, and a 524K token context window. It's available on all plans and through the API.
Mistral Large 4 at a glance
Frontier open-weight multimodal model for coding and analysis.
| Spec | Mistral Large 4 |
|---|---|
| Model ID | mistral/mistral-large-4 |
| Context window | 524K tokens |
| Released | October 6, 2026 |
| Input | $1.36 per 1M tokens |
| Output | $4.18 per 1M tokens |
| Cache read | $0.14 per 1M tokens |
| Effective input in an agent loop | $0.51 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Mistral Large 4 model page as of October 6, 2026, including any deal running that day, so they can differ from the launch pricing above.
Use Mistral Large 4
1cmd --model mistral/mistral-large-4Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Mistral Large 4
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0063 |
| Review a 500-line PR | 60K · 4K | $0.05 |
| Fix a bug (agent loop) | 180K · 12K | $0.13 |
| Refactor a module | 320K · 20K | $0.24 |
| Full-repo agent run | 900K · 45K | $0.56 |
Try Command Code
The best coding agent for open models, in your terminal or on your desktop.
1npm i -g command-codeDesktop App · Docs · X · Discord
