mistralai

Mistral: Codestral 2508

Mistral Codestral 2508 is an AI model from MistralAI that can process both text and files, with a context length of up to 256,000 tokens and the ability to generate up to 204,800 completion tokens. It supports tools for interaction but lacks built-in reasoning or structured output capabilities. While its pricing at $0.3 per million input tokens and $0.9 per million output tokens makes it relatively cost-effective for certain use cases, there are currently no independent benchmarks available to assess its performance comprehensively.

Quality Score
99/100
price + capability + benchmarks
Input Price
$0.30
per 1M tokens · checked 2026-09-07
Output Price
$0.90
per 1M tokens · checked 2026-09-07
Context Window
256,000
tokens
Model ID
mistralai/codestral-2508
Vendor
mistralai
Released
August 2025
Tokenizer
Mistral
Input Modalities
text, file
Output Modalities
text
Max Output
204,800 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.30/M input and $0.90/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.01
Classify 1,000 customer emails 500k in / 50k out $0.20
A month of a busy support chatbot 5M in / 2M out $3.30

Similar models

Quick answers

How much does Mistral: Codestral 2508 cost?
$0.30 per million input tokens and $0.90 per million output tokens.
What is Mistral: Codestral 2508's context window?
256,000 tokens, roughly 384 pages of text in a single request.
Does Mistral: Codestral 2508 support tool calling?
It supports tool calling, structured output.
Can Mistral: Codestral 2508 process images?
No, it is text-only on the input side.