# 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.
Prices as of 2026-10-04.

| 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 | $0.368 | $1.103 | $0.037 | 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

## FAQ

### What is the cheapest Codestral 2508 API?

As of Oct 4, 2026, NanoGPT has the lowest Codestral 2508 output price at $0.9 per 1M tokens, and NanoGPT has the lowest input price at $0.3 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Codestral 2508?

3 providers list Codestral 2508 on Sovyron; 3 of them sell it at a metered per-token price.

### Is Codestral 2508 free?

No provider in the Sovyron catalog lists a free tier for Codestral 2508.

### What is the context window of Codestral 2508?

Codestral 2508 supports a 256k-token context window and up to 256k output tokens.

HTML page: https://sovyron.com/models/codestral-2508/
Full dataset: https://sovyron.com/data/catalog.json