Codestral 25.08, the Mistral AI model in numbers

What you need to know

Mistral AI released Codestral 25.08 on July 30, 2025. It has no declared reasoning mode: it answers directly, without an extra billed thinking step. It is a closed model: you access it through an API, from Mistral AI or one of the 11 providers listed on models.dev. That makes it more than a year old: successors may have shipped since.

We file it under budget models (24 models in this category on the site).

What it costs

Codestral 25.08 costs $0.30 per million input tokens and $0.90 per million output tokens (developer's price, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.008; a thousand of those tasks, $7.8.

That is 1.3 times cheaper than the median output price of budget models ($1.13).

Tokens read back from cache cost $0.03 per million, which helps an agent that keeps resending the same context.

To estimate your own budget, use the agent cost calculator.

Measured performance

Epoch AI publishes a single result for Codestral 25.08 on our basket's benchmarks: too few to compute a reliable capability index.

• Aider Polyglot (code editing across several languages): 1,110% — the best tracked model, GPT-5, reaches 8,800%

Context and capabilities

Its context window reaches 256,000 tokens, roughly 384 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 8,192 tokens.

It accepts as input: text and PDF.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

What is it good for?

Given its category, Codestral 25.08 is mainly aimed at high volumes where every cent counts: sorting, information extraction, summaries, simple assistants.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to Codestral 25.08 are:

• Seed 2.0 Lite (ByteDance Seed, $0.76 per million output tokens)
• Mercury 2.5 (Inception, $0.75 per million output tokens)
• Qwen3.6 Flash (Alibaba Cloud (Qwen), index 64.5)
• CoBuddy (Baidu (ERNIE), $1.13 per million output tokens)