Mistral: Codestral 2508
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
- 109,312 Toman/M tokens
- Output
- 324,520 Toman/M tokens
- Context
- 256K
- Max output
- 205K
- Published
- Aug 1, 2025
- Maker
- Mistral
Free plan prices, in Toman at today's rate. Plans and prices
Price by plan
Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period.
| Plan | Input | Output |
|---|---|---|
| Free | 109,312 | 324,520 |
| Pro | 104,832 | 311,220 |
| Max | 100,352 | 297,920 |
Capabilities
- Text
- Tools
- JSON
What it takes and gives
Accepts
- Text
- File (PDF)
Creates
- Text
Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.
Call it
Pass mistralai/codestral-2508 as the model name, or let router/auto choose for you.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://ai.fluxcdn.cloud/api/v1",
api_key=os.environ["FLUXCDN_API_KEY"],
)
resp = client.chat.completions.create(
model="router/auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
