Codestral 2508

Mistral AImistralai/codestral-2508Providers: 2
Inputi$0.30per 1M tokens
Outputi$0.90per 1M tokens
Contexti256K256,000 tokens
ReleasedAug 1, 2025Max output: 200K

About this model

Codestral 2508 is an AI model from Mistral AI, made available through the API on August 1, 2025. It can read up to 256,000 tokens in one request, roughly 480 pages of text, and write up to 204,800 tokens in a single answer. Besides text, it accepts files such as PDFs as input.

Through the API it costs $0.30 per million input tokens and $0.90 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.

It can call tools and functions, so developers can connect it to search, databases or other software.

Quality scores

Rankings →

Not rated yet. Independent test results usually appear a few weeks after a model is released.

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 2. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
MistralOfficialCheapest
$0.30$0.90256K99.8%
MistralOfficial
$0.33$0.99256K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call Codestral 2508 through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/codestral-2508", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $0.42
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.016
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $198

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
$0.30$1.50192KCompare with ⇄
$0.30$1.201MCompare with ⇄
Gemini 3.5 Flash LiteGoogle DeepMind
$0.30$2.501MCompare with ⇄
$0.30$1.201MCompare with ⇄
MiniMax M3MiniMax
$0.30$1.201MCompare with ⇄
$0.30$1.801MCompare with ⇄

News about Mistral AI

See all →

Frequently asked questions

How much does Codestral 2508 cost?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.42.
What is the context window of Codestral 2508?
Codestral 2508 can read up to 256,000 tokens in one request, about 480 pages of text. It can write up to 204,800 tokens in a single answer.
Is Codestral 2508 open source?
No. Codestral 2508 is a closed model: its weights are not published, so you use it through Mistral AI’s own apps and API, or through cloud providers.
Who makes Codestral 2508?
Codestral 2508 is made by Mistral AI. It became available through the API on August 1, 2025.
Can Codestral 2508 read images?
Yes. Besides text, it accepts files such as PDFs as input.
What are the alternatives to Codestral 2508?
Models with a similar price from other companies include Command A+, DeepSeek V4.1 Flash and Gemini 3.5 Flash Lite. You can compare them side by side on this page.