Codestral 2508
Mistral AIReleased Aug 1, 2025
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)
- Context window
- 256K tokens
- Input
- text, file
- Output
- text
- Tokenizer
- Mistral
- Knowledge cutoff
- Mar 31, 2025
- Released
- Aug 1, 2025
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.300 | $0.0090 | $0.309 |
| Output | $0.900 | $0.027 | $0.927 |
| Cache read | $0.030 | $0.0009 | $0.031 |
Benchmarks
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| Codemodels | 1057 | 38.5% | #89 |
| Data vizmodels | 1062 | 41.7% | #83 |
| Game devmodels | 1032 | 36.2% | #91 |
| UI componentsmodels | 1073 | 46.9% | #78 |
| Websitesmodels | 1055 | 37.8% | #92 |
| 3Dmodels | 1097 | 45.5% | #76 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- max_tokens
- presence_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model mistralai/codestral-2508.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/codestral-2508",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "mistralai/codestral-2508",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Codestral 2508 cost via API?
- Through OpenKey, Codestral 2508 costs $0.309 per 1M input tokens and $0.927 per 1M output tokens. That is the provider price ($0.300 / $0.900) plus a flat 3% fee — nothing else.
- What is Codestral 2508's context window?
- Codestral 2508 accepts up to 256K tokens of context.
- Is Codestral 2508 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "mistralai/codestral-2508" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Codestral 2508 support?
- Codestral 2508 accepts text, file input and produces text output. Its knowledge cutoff is Mar 31, 2025.
More from Mistral AI
All Mistral AI models →Mistral Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
ctx 262Kin $1.54out $7.73
Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
ctx 262Kin $0.154out $0.618
Devstral 2 2512
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
ctx 262Kin $0.412out $2.06
Ministral 3 14B 2512
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
ctx 262Kin $0.206out $0.206