Full Model Pricing
Model profile

Mistral: Codestral 2508

mistralai chat
mistralai/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](https://mistral.ai/news/codestral-25-08)

At a glance

Model specifications

The most important technical and pricing details in one place.

Context window
256K tokens
Model type
Chat
Input / 1M
$0.30
Output / 1M
$0.90

Providers and routing order

Gateway-compatible routes are tried from the lowest cost; other sources are shown for catalog reference.

2 sources
1
Mistral AIGateway activecodestral-2508 · Updated 05.10.2026 19:17
Input$0.0000 / 1M Output$0.0000 / 1M Cache$0.0000 / 1M Media-
2
OpenRouterGateway activemistralai/codestral-2508 · Updated 05.10.2026 19:17
Input$0.3000 / 1M Output$0.9000 / 1M Cache$0.0300 / 1M Media-
Live telemetry

Usage and performance

Current request, token, and latency data across TamgaStudio.

Usage Example

Call Mistral: Codestral 2508 with a single request through the OpenAI-compatible TamgaStudio API. Create your API key from the API Keys section in your dashboard.

curl https://api.tamga.studio/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tl-sk-XXXXXX" \
  -d '{"model": "mistralai/codestral-2508", "messages": [{"role": "user", "content": "Hello!"}]}'
import requests

resp = requests.post(
    "https://api.tamga.studio/v1/chat/completions",
    headers={"Authorization": "Bearer tl-sk-XXXXXX"},
    json={
        "model": "mistralai/codestral-2508",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(resp.json()["choices"][0]["message"]["content"])
<?php
$ch = curl_init('https://api.tamga.studio/v1/chat/completions');
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer tl-sk-XXXXXX',
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'model' => 'mistralai/codestral-2508',
        'messages' => [['role' => 'user', 'content' => 'Hello!']],
    ]),
    CURLOPT_RETURNTRANSFER => true,
]);
echo curl_exec($ch);

Frequently Asked Questions

Common questions about this model.

What is 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](https://mistral.ai/news/codestral-25-08) It is accessible through a single OpenAI-compatible API via TamgaStudio.
How much does Mistral: Codestral 2508 cost?
Pricing is $0.30 per 1M input tokens and $0.90 per 1M output tokens. Billing is credit-based: you only pay for what you use.
What is the context length of Mistral: Codestral 2508?
Mistral: Codestral 2508 supports a context of up to 256,000 tokens in one request.
Can I use Mistral: Codestral 2508 with the OpenAI SDK?
Yes. TamgaStudio exposes all models through an OpenAI-compatible endpoint: https://api.tamga.studio/v1/chat/completions. Just swap the base URL and API key in your existing OpenAI code.
How do I get an API key?
After signing in, create a key from the "API Keys" section of your dashboard. The key is shown only once and is stored as a SHA-256 hash.