uttapen
Create an API key

Saba API: toman pricing and code

mistralai/mistral-saba

toolsjsonfiles
Create a keyTry it
Input · per 1M tokens
58,025 toman
Output · per 1M tokens
174,075 toman
One 1,000-word request ≈
302 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 5,803 toman / 1M.Pricing and top-ups

Saba example: tool calling

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="mistralai/mistral-saba", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="mistralai/mistral-saba", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is Saba good for?

Saba comes from Mistral; in uttapen you reach it with the model id "mistralai/mistral-saba". It accepts up to 32,768 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 26,214 tokens. On price it sits in the "very cheap" band — cheaper than 95 and dearer than 311 of the other paid models in the catalogue.

What it can do beyond plain text: it takes files such as PDFs as input; it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Pricing is 58,025 toman per 1M input tokens and 174,075 per 1M output tokens. A 1,000-word round trip on Saba lands near 302 toman. It supports cached input: repeated context is billed at 5,803 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is Command R (08-2024): Saba works out roughly 1.1× more expensive, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 331 thousand-word requests on Saba, and every 1,000 toman is about 3,311 words of round trip. A job with one million input tokens and one million output tokens comes to 232,100 toman in total. Filling this model's 32,768-token window costs 1,901 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "mistralai/voxtral-small-24b-2507", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 2× dearer (302 against 151 toman).

Mistral has 20 models in our catalogue; the cheapest is Mistral Nemo at 18 toman per thousand words and the dearest Mistral Medium 3.5 at 3,394. It does not support include_reasoning, reasoning, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Aion-RP 1.0 (8B) at 32,768 tokens.

Good fits: high-volume work such as classification, tagging and bulk summarising, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

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...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out157 toman
Summarising a ten-page document4,000 in + 600 out337 toman
Classifying a thousand short rows120,000 in + 20,000 out10,445 toman

Frequently asked

How do I call Saba from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "mistralai/mistral-saba". Nothing else in your code changes.
What does Saba cost in toman?
58,025 toman per 1M input tokens and 174,075 toman per 1M output tokens; a 1,000-word request is around 302 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Saba take?
Up to 32,768 tokens per request, roughly 25k words. A single answer can reach 26,214 tokens.
Does Saba support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.