uttapen
Create an API key

Granite 4.2 8B API: toman pricing and code

ibm-granite/granite-4.2-8b

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
29,013 toman
Output · per 1M tokens
43,519 toman
One 1,000-word request ≈
94 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 14,506 toman / 1M.Pricing and top-ups

Granite 4.2 8B 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-4.2-8b",
    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 4.2 8B good for?

IBM Granite publishes this model; we expose it under the id "ibm-granite/granite-4.2-8b". Its context window is 131,072 tokens, roughly 98k English words in one request. A single response can run to 117,964 tokens. On price it sits in the "very cheap" band — cheaper than 19 and dearer than 387 of the other paid models in the catalogue.

What it can do beyond plain text: 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; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Pricing is 29,013 toman per 1M input tokens and 43,519 per 1M output tokens. A 1,000-word round trip on Granite 4.2 8B lands near 94 toman. It supports cached input: repeated context is billed at 14,506 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 Mercury 2.5 Preview: Granite 4.2 8B works out roughly 1.3× 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 1,064 thousand-word requests on Granite 4.2 8B, and every 1,000 toman is about 10,638 words of round trip. A job with one million input tokens and one million output tokens comes to 72,531 toman in total. Filling this model's 131,072-token window costs 3,803 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, reasoning_effort, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is Aion-2.0 at 131,072 tokens.

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

Provider's own description

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

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 out61 toman
Summarising a ten-page document4,000 in + 600 out142 toman
Classifying a thousand short rows120,000 in + 20,000 out4,352 toman

Frequently asked

How do I call Granite 4.2 8B 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-4.2-8b". Nothing else in your code changes.
What does Granite 4.2 8B cost in toman?
29,013 toman per 1M input tokens and 43,519 toman per 1M output tokens; a 1,000-word request is around 94 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Granite 4.2 8B take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 117,964 tokens.
Does Granite 4.2 8B 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.