Mistral: Codestral 2508: AI model
Codestral 2508 is Mistral's coding-tuned model for fast fill-in-the-middle, code fixes and test generation, with a 256K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 256,000 tokens
- Input:
- $0.3/1M tokens
- Output:
- $0.9/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Codestral 2508 is a coding-specialized model from the Mistral family, tuned for the high-frequency, low-latency tasks developers hit all day: fill-in-the-middle completion, correcting existing code, and generating tests. Its 256K-token context window is large enough to hold sizeable files and surrounding modules while it works.
Because it favors speed on short, frequent requests, Codestral 2508 fits well inside editors, IDE plugins and CI helpers where latency is felt directly. It supports tool calling, so you can wire it into automated coding pipelines. It is served through Hormouz behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.
Pricing is usage-based: $0.3 per million input tokens and $0.9 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
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
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/codestral-2508",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Mistral AI |
|---|---|
| Type | Text |
| Context window | 256,000 tokens |
| Pricing | $0.30/M in · $0.90/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/codestral-2508",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "mistralai/codestral-2508",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Mistral: Codestral 2508 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Mistral: Codestral 2508 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Codestral 2508 cost?
- Billing is usage-based: $0.3 per million input tokens and $0.9 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Codestral 2508 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Codestral 2508 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- What coding tasks is Codestral 2508 best at?
- It is tuned for fill-in-the-middle completion, correcting existing code, and generating tests. The fast, frequent tasks that happen inside an editor rather than long one-shot generations.
- Does Codestral 2508 support tool calling?
- Yes. It supports tool calling, so you can connect it to automated coding workflows, agents and CI helpers through the OpenAI-compatible API on Hormouz.
Updated 2026-10-13