Codestral 2508
Mistral's cutting-edge language model for coding released end of July 2025.
Input per 1M
$0.315
Output per 1M
$0.945
Context
256Ktokens
Per 1M tokens
$0.315 · $0.945
Context
256Ktokens
Supports
- Calls tools
opencode.json
export ANTHROPIC_BASE_URL="https://deference.si"
export ANTHROPIC_AUTH_TOKEN="$DEFERENCE_API_KEY"
export CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY="1"
claude --model mistralai/codestral-2508model = "mistralai/codestral-2508"
model_provider = "deference"
web_search = "disabled"
[model_providers.deference]
name = "Deference"
base_url = "https://deference.si/v1"
wire_api = "responses"
env_key = "DEFERENCE_API_KEY"# Cursor › Settings › Models
OpenAI API Key: your sk-df-… key
Override OpenAI Base URL: https://deference.si/v1
Add model: mistralai/codestral-2508{
"provider": {
"deference": {
"npm": "@ai-sdk/openai-compatible",
"options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
"models": { "mistralai/codestral-2508": { "limit": { "context": 256000, "output": 204800 } } }
}
}
}curl https://deference.si/v1/chat/completions \
-H "Authorization: Bearer $DEFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/codestral-2508",
"messages": [{ "role": "user", "content": "Say hello in one sentence." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://deference.si/v1", api_key=os.environ["DEFERENCE_API_KEY"])
completion = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://deference.si/v1", apiKey: process.env.DEFERENCE_API_KEY });
const completion = await client.chat.completions.create({
model: "mistralai/codestral-2508",
messages: [{ role: "user", content: "Say hello in one sentence." }],
});
console.log(completion.choices[0].message.content);Needs an API keyGet one
Pricing and limits
- Cache read$0.0315per 1M tokens
- Max output204,800tokens
OpenRouter's price plus OpenRouter's 5% platform fee. Deference adds no markup.