Mistral: Saba: AI model
Mistral Saba is a 24B model tuned for the Middle East and South Asia, delivering strong regional and multilingual quality with a 32K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 32,768 tokens
- Input:
- $0.2/1M tokens
- Output:
- $0.6/1M tokens
- Type:
- text
- Tools
- Streaming
Mistral Saba is a 24B-parameter model from the Mistral family designed with the Middle East and South Asia in mind. It is trained to give accurate, contextually appropriate responses for the languages and cultural context of those regions while staying efficient to run.
That regional focus makes it a good fit for products serving users across the region, including Persian-language use cases. It offers a 32K-token context window and supports tool calling. 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: $0.2 per million input tokens and $0.6 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-saba",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Mistral AI |
|---|---|
| Type | Text |
| Context window | 32,768 tokens |
| Pricing | $0.20/M in · $0.60/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Benchmarks
Reasoning
Source: Artificial Analysis
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/mistral-saba",
"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/mistral-saba",
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/mistral-saba",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Mistral: Saba API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Mistral: Saba 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 Mistral Saba cost?
- Billing is usage-based: $0.2 per million input tokens and $0.6 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Mistral Saba 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 Mistral Saba 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 is Mistral Saba specialized for?
- It is tuned for the Middle East and South Asia, aiming for accurate, contextually appropriate responses in the languages and cultural context of those regions, which includes Persian-language use cases.
- Is Mistral Saba a good fit for Persian-language products?
- Its regional focus on the Middle East makes it a reasonable choice for products serving Persian and neighboring-language users, with a 32K-token context window and tool calling.
Updated 2026-10-13