Mistral Codestral

Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Model overview

Model ID: mistral/codestral
Provider: mistral
Type: language
Context window: 128,000 tokens
Max output tokens: 4,000

Tags: tool-use

Model pricing

Metric	Value
`Input tokens (/1M)`	`$0.30`
`Output tokens (/1M)`	`$0.90`
`Image generation`	`n/a`
`Cached input read (/1M)`	`n/a`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix