CheapestCoding Long-contextBest value Get an API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › mistralai › Mistral: Codestral 2508

Mistral: Codestral 2508 — pricing & benchmarks

By mistralai · Updated 2026-07-24 · cheap high-volume

Mistral: Codestral 2508 costs $0.3 per 1M input tokens and $0.9 per 1M output tokens, with a 256K context window. It is best suited for cheap high-volume, and is available through one OpenAI-compatible Appmo API key.
$0.3Input / 1M
$0.9Output / 1M
256KContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What Mistral: Codestral 2508 is used for

Mistral: Codestral 2508 is best suited for cheap high-volume. Access it through one Appmo API key alongside 390 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"mistralai/codestral-2508","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Mistral: Codestral 2508 cost?
Mistral: Codestral 2508 costs $0.3 per 1M input tokens and $0.9 per 1M output tokens ($0.45 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is Mistral: Codestral 2508 best for?
Mistral: Codestral 2508 is best suited for cheap high-volume.

How do I use Mistral: Codestral 2508?
Send requests to Appmo's OpenAI-compatible endpoint with model id "mistralai/codestral-2508" and one API key — no separate provider account needed.