How much does Codestral Embed cost?

Billing is usage-based: $0.15 per million input tokens. There is no fixed monthly fee. You pay only for the text you embed.

Is Codestral Embed compatible with OpenAI code?

Yes. Hormouz exposes an OpenAI-compatible API, so you call the standard embeddings endpoint. Change the base URL to Hormouz and swap in your Hormouz key. Your existing client libraries work without a rewrite.

What is Codestral Embed used for?

It converts code and code-related text into vectors for semantic search over repositories, code databases and RAG pipelines. Powering code search and retrieval in coding assistants rather than generating text.

Does Codestral Embed generate text or images?

No. It is an embedding model: the output is a numeric vector per input, used for similarity, search and ranking. For chat or code generation you would use a text model such as Codestral 2508.

Mistral: Codestral Embed 2505: AI model

Codestral Embed is Mistral's code-specialized embedding model for indexing repositories and powering retrieval in coding assistants. Reachable from inside Iran through Hormouz.

Context window:: 8,192 tokens
Input:: $0.15/1M tokens
Output:: $0/1M tokens
Type:: embedding

Embeddings

Codestral Embed is an embedding model from the Mistral family built specifically for code. Instead of generating text, it turns source code and code-related text into dense numeric vectors that capture meaning, so similar snippets land near each other in vector space.

That makes it a strong fit for indexing repositories and code databases, building code search, and adding retrieval to coding assistants and RAG pipelines. Its 8K-token input window lets you embed sizeable files or chunks in one call. 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 against the embeddings endpoint.

Pricing is usage-based: $0.15 per million input tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.

Quickstart

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/codestral-embed-2505","input":"The quick brown fox"}'

Specs

Vendor	Mistral AI
Type	Embedding
Context window	8,192 tokens
Pricing	$0.15/M in · $0.00/M out
API	embeddings

Code example

cURL

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/codestral-embed-2505","input":"The quick brown fox"}'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
resp = client.embeddings.create(model="mistralai/codestral-embed-2505", input="The quick brown fox")
print(resp.data[0].embedding)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const resp = await client.embeddings.create({
  model: "mistralai/codestral-embed-2505",
  input: "The quick brown fox",
});
console.log(resp.data[0].embedding);

Buy the Mistral: Codestral Embed 2505 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral: Codestral Embed 2505 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.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Codestral Embed cost?: Billing is usage-based: $0.15 per million input tokens. There is no fixed monthly fee. You pay only for the text you embed.
How do I access Codestral Embed 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 Embed compatible with OpenAI code?: Yes. Hormouz exposes an OpenAI-compatible API, so you call the standard embeddings endpoint. Change the base URL to Hormouz and swap in your Hormouz key. Your existing client libraries work without a rewrite.
What is Codestral Embed used for?: It converts code and code-related text into vectors for semantic search over repositories, code databases and RAG pipelines. Powering code search and retrieval in coding assistants rather than generating text.
Does Codestral Embed generate text or images?: No. It is an embedding model: the output is a numeric vector per input, used for similarity, search and ranking. For chat or code generation you would use a text model such as Codestral 2508.

Updated 2026-10-13