opendunes

Codestral 2508

by MistralReleased 1 August 2025

Codestral 2508 is Mistral's code model for fast, repeated edits inside an editor: you send the code before and after a gap and it fills the middle, corrects errors and writes tests. It reads about 256 pages of text or files and answers in text. Pick it for autocomplete where waiting counts.

TakesTextFiles
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,25 DA per message3 000 DA buys about 12 000 messages

One message, the ordinary use

1 000 tokens sent× 99,85 DA per 1M0,10 DA
500 tokens back× 299,55 DA per 1M0,15 DA
Total≈ 0,25 DA

Every rate

Meter↑ you send↓ comes back
Text tokens99,85 DA299,55 DA
Cached tokens read9,99 DA

per 1M tokens

Complete a line of code≈ 0,17 DA
Explain an error log and suggest a fix≈ 0,43 DA
Write a small web page component≈ 0,53 DA
Write unit tests for one module≈ 0,84 DA
Review a pull request of about 400 lines≈ 0,96 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Mistral…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
299,55 DA
Cache read
9,99 DA
Latency
…
Throughput
…
MistralEurope…
↑ Sent, per 1M
109,84 DA
↓ Back, per 1M
329,51 DA
Cache read
10,98 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Mistral99,85 DA299,55 DA9,99 DA………
MistralEurope109,84 DA329,51 DA10,98 DA………

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
mistralai/codestral-2508
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="mistralai/codestral-2508",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_pstopseedfrequency_penaltypresence_penalty

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Other

Also accepted by this model.

prediction

Questions about Codestral 2508

  • How much does Codestral 2508 cost in dinars?

    About 0,25 DA per message. ↑ 99,85 DA · ↓ 299,55 DA per 1M tokens.

  • Is Codestral 2508 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Codestral 2508 best for?

    Codestral 2508 is Mistral's code model for fast, repeated edits inside an editor: you send the code before and after a gap and it fills the middle, corrects errors and writes tests. It reads about 256 pages of text or files and answers in text. Pick it for autocomplete where waiting counts.

  • How do I pay for Codestral 2508 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Codestral 2508 included, is paid from that balance. No foreign card, no conversion.

  • Does Codestral 2508 work in Arabic, French or Darja?

    Mistral names no languages for Codestral 2508. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text and PDFs. Up to 256K tokens in one request, about 250 pages. It writes up to 154 000 words at once.

  • Is Codestral 2508 open source?

    No. Mistral has not published its weights.

  • Who makes Codestral 2508, and when was it released?

    Mistral. Released 1 August 2025. It knows the world up to 31 March 2025.

Other Mistral models, priced in dinars

See all Mistral models
Voxtral Small Transcribe 3Mistral · Oct 20, 2026

Mistral's flagship speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, with context biasing for domain-specific vocabulary

1,46 DAper minute of audio
View model
Voxtral Mini TranscribeMistral · May 15, 2026

The Voxtral Mini derivative that only transcribes, taking audio from meetings, voice notes and podcasts and returning the text through a standard transcription request

1,10 DAper minute of audio
View model
Voxtral Mini Transcribe 3Mistral · Oct 20, 2026

Mistral's compact speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, and can be steered with context biasing to catch domain terms

1,28 DAper minute of audio
View model
Mistral Embed 2312Mistral · Oct 31, 2025

Mistral AI's text embedding model from late 2023, whose 1024-dimension vectors capture how passages relate, for semantic search and RAG; Codestral Embed is the version for code

8 pages per call
≈0,033 DAper page
View model