# Codestral 2508 API prices

Codestral 2508 (codestral) — 256k context, 256k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.3 | $0.9 | $0.15 | 256k |
| OpenRouter | $0.3 | $0.9 | $0.03 | 256k |
| Cortecs | $0.334 | $1.003 | $0.033 | 256k |

## Summary

- Cheapest input: $0.3 per 1M tokens (NanoGPT)
- Cheapest output: $0.9 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-08-01
- Inputs: pdf, text

HTML page: https://llmprice.gitlab.io/models/codestral-2508/
Full dataset: https://llmprice.gitlab.io/data/catalog.json