# Codestral API prices

Codestral (codestral) — 256k context, 256k max output.
6 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Eden AI | $0.3 | $0.9 | $0.03 | 256k |
| DevPass (LLM Gateway) | $0.3 | $0.9 | — | 256k |
| LLM Gateway | $0.3 | $0.9 | — | 256k |
| Merge Gateway | $0.3 | $0.9 | — | 256k |
| Mistral | $0.3 | $0.9 | — | 256k |
| Vercel AI Gateway | $0.3 | $0.9 | — | 256k |

## Summary

- Cheapest input: $0.3 per 1M tokens (Eden AI)
- Cheapest output: $0.9 per 1M tokens (Eden AI)
- First-party: $0.9 per 1M output tokens (Mistral)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-05-29
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/codestral/
Full dataset: https://llmprice.gitlab.io/data/catalog.json