Skip to content
LLMs
Mistral AI logo

Mistral: Codestral 2508

by Mistral AI

Mistral: Codestral 2508 is a large language model from Mistral AI. It costs $0.300 per million input tokens and $0.900 per million output tokens. Its context window is 256K tokens.

Tool callingStructured outputPrompt cachingBatch tierfile input
Input / 1M tokens
$0.300
Output / 1M tokens
$0.900
Cached input / 1M
$0.030

On repeated prefixes

Context window
256K

tokens

Who serves it cheapest

1 hosts serve Codestral 2508. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Codestral 2508, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
MistralCheapest$0.300$0.900256K-99.9%

About Codestral 2508

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. [Blog Post](https://mistral.ai/news/codestral-25-08)

Specifications

Mistral: Codestral 2508 specifications
Model IDmistralai/codestral-2508
ProviderMistral AI
Context window256K tokens
Max output205K tokens
Input modalitiestext, file
Output modalitiestext
Knowledge cutoff2025-03-31
Open weightsNo
ReleasedAugust 1, 2025

Cheaper alternatives

Models that cost less than Codestral 2508 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Mistral: Codestral 2508 cost?

$0.300 per million input tokens and $0.900 per million output tokens. Cached input reads cost $0.030 per million tokens.

What is the context window of Mistral: Codestral 2508?

256K tokens, with up to 205K tokens of output per request.

Confirm against the source: Mistral AI official pricing.