Codestral 2508 as a coding agent in your terminal
Codestral 2508 by Mistral AI, one of 250+ models you can use in Darce, the open source AI coding agent you can undo.
| Model | Codestral 2508 |
|---|---|
| Vendor | Mistral AI |
| Model id | mistralai/codestral-2508 |
| Context window | 256k tokens |
| Price per 1M tokens | $0.30 input · $0.90 output (OpenRouter) |
| Can do | tool calling |
| Category | Coding-tuned |
Strengths
Mistral's Codestral, a fast, low-cost model specialised in code.
OpenRouter's description:
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Use Codestral 2508 as a coding agent in your terminal
Start Darce in your project with Codestral 2508:
npm install -g darce-cli
darce --model mistralai/codestral-2508Already in a session? Type /model mistralai/codestral-2508, or open the picker with Ctrl+P. Darce then reads your code, edits files and runs commands with Codestral 2508; risky commands ask first, and /undo reverses any change, including what shell commands did. No account yet? npx darce-cli lets you try it free. Which plan includes which models is on the pricing page.
Make it your default or a gear
In ~/.darcerc, set it as the starting model or add it to the gears you move between with Shift+↑ / Shift+↓ (see configuration):
{
"router": { "default": "mistralai/codestral-2508" },
"gears": ["qwen/qwen3-coder", "mistralai/codestral-2508"]
}Compare it on your own code
Benchmarks rarely match your repository. Race Codestral 2508 against two other models on a real task and keep the best diff:
/derby --models mistralai/codestral-2508,mistralai/devstral-2512,mistralai/mistral-large-4-0 fix the failing testRead more about /derby and /swarm.
Related models
- Devstral 2 2512 (Mistral AI): 262k tokens, $0.40 / $2.00 per 1M tokens
- Mistral Large 4 (Mistral AI): 1.05M tokens, $0.68 / $2.09 per 1M tokens
- GPT-5.3-Codex (OpenAI): 400k tokens, $1.75 / $14.00 per 1M tokens
- Qwen3 Coder 480B A35B (Qwen (Alibaba)): 262k tokens, $0.30 / $1.00 per 1M tokens
- Qwen3 Coder Next (Qwen (Alibaba)): 262k tokens, $0.12 / $0.80 per 1M tokens
- Qwen3 Coder Plus (Qwen (Alibaba)): 1M tokens, $0.65 / $3.25 per 1M tokens
All models · Getting started · Claude Code alternative
Model data from OpenRouter, refreshed daily. Prices are OpenRouter's list rates and show relative cost; your Darce allowance is used in proportion to them.