Codestral 2508 API
Run codestral-2508 through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
Codestral 2508 pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | $0.32 |
| Output | $0.95 |
Served by 2 providers
Requests route to OpenRouter by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| openrouter | mistralai/codestral-2508 |
| mistral | codestral-2508 |
Call Codestral 2508 in 30 seconds
Works with any OpenAI SDK — change the base URL and API key only.
Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")
response = client.chat.completions.create(
model="codestral-2508",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl
curl https://api.fastinfra.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codestral-2508",
"messages": [{"role": "user", "content": "Hello!"}]
}'Codestral 2508 — common questions
How much does the codestral-2508 API cost?
On FastInfra, codestral-2508 costs $0.315/1M input, $0.945/1M output tokens. Billing is per token used, with no subscription.
Is codestral-2508 compatible with the OpenAI SDK?
Yes. FastInfra exposes codestral-2508 through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.
Which providers serve codestral-2508?
codestral-2508 is available from 2 provider(s): openrouter, mistral. Requests route to OpenRouter by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: Codestral 2508 vs Mistral:7b · Codestral 2508 vs Mistral Nemo · Codestral 2508 vs Mistral Nemo Instruct 2407