Codestral 2508
Mistral Codestral 2508 — pricing, 256k context window, API cost calculator and alternatives.
By Mistral
Specs
- Provider
- Mistral
- Slug
- mistralai/codestral-2508
- Capabilities
- tools, json_mode
Pricing freshness
- Tier
- standard
- Currency
- USD
- As of
- 2026-05-08 17:08 UTC
Pricing history
Tracking Codestral 2508 pricing since 2026-05-08. We'll plot the chart here once it changes.
Quickstart — call Codestral 2508 from your app
curl https://api.mistral.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-d '{
"model": "codestral-2508",
"messages": [{"role": "user", "content": "Hello!"}]
}'Official docs: https://docs.mistral.ai/api/
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.mistral.ai/v1",
api_key=os.environ["MISTRAL_API_KEY"],
)
resp = client.chat.completions.create(
model="codestral-2508",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Official docs: https://docs.mistral.ai/api/
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.mistral.ai/v1",
apiKey: process.env.MISTRAL_API_KEY,
});
const resp = await client.chat.completions.create({
model: "codestral-2508",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Official docs: https://docs.mistral.ai/api/
Related models
Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.
Frequently asked questions
What is Codestral 2508?
Codestral 2508 is a large language model API from Mistral with a 256k-token context window. It costs $0.3 per 1M input tokens and $0.9 per 1M output tokens.
How much does Codestral 2508 cost?
Codestral 2508 is priced at $0.3 per 1M input tokens and $0.9 per 1M output tokens via the Mistral API. A 50/50 input/output workload of 1M total tokens costs about $0.6.
What is the context window of Codestral 2508?
Codestral 2508 supports up to 256k tokens of context per request — roughly 512 pages of English text or 32000 lines of code at a typical density.
Does Codestral 2508 support vision, tool use, or JSON mode?
Codestral 2508 supports tool/function calling and structured JSON mode. It does not support image input (vision).
Who makes Codestral 2508?
Codestral 2508 is built and operated by Mistral. Pricing, context window, and capabilities on this page are refreshed nightly from Mistral's public catalog.
Can I self-host Codestral 2508?
Codestral 2508 is API-only — its weights are not publicly distributed by Mistral, so it cannot be self-hosted today.