uttapen
Create an API key

Granite 4.0 Micro API: toman pricing and code

ibm-granite/granite-4.0-h-micro

json
Create a keyTry it
Input · per 1M tokens
4,932 toman
Output · per 1M tokens
32,494 toman
One 1,000-word request ≈
49 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

Granite 4.0 Micro example: JSON output against a schema

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-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="ibm-granite/granite-4.0-h-micro",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is Granite 4.0 Micro good for?

Granite 4.0 Micro comes from IBM Granite; in uttapen you reach it with the model id "ibm-granite/granite-4.0-h-micro". It accepts up to 131,000 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 117,900 tokens. On price it sits in the "very cheap" band — cheaper than 12 and dearer than 394 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 49 toman per 1,000-word exchange (4,932 in, 32,494 out, per 1M tokens). 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 Phi 4: Granite 4.0 Micro works out roughly 1.6× cheaper, and its context window is larger. 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 2,041 thousand-word requests on Granite 4.0 Micro, and every 1,000 toman is about 20,408 words of round trip. A job with one million input tokens and one million output tokens comes to 37,426 toman in total. Filling this model's 131,000-token window costs 646 toman on the input side alone, which is the real reason to keep conversation history short.

IBM Granite has 2 models in our catalogue; the cheapest is Granite 4.0 Micro at 49 toman per thousand words and the dearest Granite 4.2 8B at 94. Among the less common parameters it accepts logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. It does not support include_reasoning, reasoning, tool_choice, tools, 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-2.0 at 131,072 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, extracting data against a fixed schema.

Provider's own description

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

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 out20 toman
Summarising a ten-page document4,000 in + 600 out39 toman
Classifying a thousand short rows120,000 in + 20,000 out1,242 toman

Frequently asked

How do I call Granite 4.0 Micro 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 "ibm-granite/granite-4.0-h-micro". Nothing else in your code changes.
What does Granite 4.0 Micro cost in toman?
4,932 toman per 1M input tokens and 32,494 toman per 1M output tokens; a 1,000-word request is around 49 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Granite 4.0 Micro take?
Up to 131,000 tokens per request, roughly 98k words. A single answer can reach 117,900 tokens.
Can I stream Granite 4.0 Micro's output?
Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.