# Codestral API prices

Codestral (codestral) — 256k context, 256k max output.
6 metered per-token offers from 6 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| 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 | $0.03 | 256k |
| Vercel AI Gateway | $0.3 | $0.9 | $0.03 | 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

## FAQ

### What is the cheapest Codestral API?

As of Oct 4, 2026, Eden AI has the lowest Codestral output price at $0.9 per 1M tokens, and Eden AI 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 much does Codestral cost on Mistral?

Mistral charges $0.3 per 1M input tokens and $0.9 per 1M output tokens for Codestral.

### How many providers offer Codestral?

6 providers list Codestral on Sovyron; 6 of them sell it at a metered per-token price.

### Is Codestral free?

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

### What is the context window of Codestral?

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

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