Codestral 2508
by MistralReleased Aug 1, 2025
mistralai/codestral-2508- Reads files and PDFs
- Calls tools
- Answers in a JSON schema
- Caches long prompts
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
- Input / 1M tokens
- $0.36
- Output / 1M tokens
- $1.08
- Context
- 256K
- Longest answer
- 205K
What it costs
What each call is charged to the token's AI credit.
| Billed for | You pay |
|---|---|
| Input tokens | $0.36 / 1M |
| Output tokens | $1.08 / 1M |
| Cached input, read | $0.036 / 1M |
A typical call
A short chat turn: 2,000 tokens in, 500 out.
- per call
- $0.0013
- calls per $20
- 16K
What it can do
From its listing. The router passes every field through.
- Reads imagesNo
- Reads files and PDFsYes
- Hears audioNo
- Calls toolsYes
- Answers in a JSON schemaYes
- Reasons before it answersNo
- Searches the webNo
- Caches long promptsYes
- Draws imagesNo
Call it
Any router key works, in the format your SDK already speaks.
import OpenAI from "openai";const ai = new OpenAI({ baseURL: "https://relayfor.si/api/v1", apiKey: process.env.RELAYFOR_ROUTER_KEY,});const reply = await ai.chat.completions.create({ model: "mistralai/codestral-2508", messages: [{ role: "user", content: "Welcome the 1,000th holder in one line." }],});Specifications
What its maker and providers list for it.
- Reads
- Text and Files
- Writes
- Text
- Context
- 256,000 tokens
- Longest answer
- 204,800 tokens
- Knowledge cutoff
- Mar 31, 2025
- Released
- Aug 1, 2025
- Moderation
- None
Request fields
The fields its providers accept, passed through as you send them.
- frequency_penalty
- max_tokens
- prediction
- presence_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Questions
How much does Codestral 2508 cost?
$0.36 per million input tokens and $1.08 per million output tokens, paid from the token's AI credit. A call of 2,000 tokens in and 500 out costs about $0.0013.
How do I call Codestral 2508?
Make a router key for one of your tokens on the dashboard, point any OpenAI or Anthropic SDK at https://relayfor.si/api/v1 and send the model id mistralai/codestral-2508. The token's AI credit pays for each call.
How long a prompt can Codestral 2508 take?
Up to 256,000 tokens of context, and up to 204,800 tokens in one answer.
Are my prompts stored?
No. The RFS Router passes each call through and keeps only its token counts and cost, for the token's usage page.
More from Mistral
Output price per 1M tokens
Similar in price
Output price per 1M tokens
