IBM Granite models, priced in toman
1 IBM Granite models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
IBM Granite on uttapen
IBM Granite currently has 1 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The cheapest IBM Granite model here is Granite 4.2 8B: roughly 140 toman for a 1,000-word request.
On capabilities: 1 supports tool calling, 1 does multi-step reasoning. The longest context belongs to Granite 4.2 8B, at 131,072 tokens.
Every IBM Granite model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which IBM Granite model should I start with?
Every IBM Granite model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Granite 4.2 8Bibm-granite/granite-4.2-8b | Tool callingReasoningJSON output | 131,072 | 20,773 | 86,555 |
Common questions about the IBM Granite API
- How do I reach the IBM Granite API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the IBM Granite model id. No international card, no VPN. - What do IBM Granite models cost in toman?
- It depends on the model: the cheapest, Granite 4.2 8B, is about 140 toman for a 1,000-word request, and the dearest, Granite 4.2 8B, about 140 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many IBM Granite models are on uttapen?
- 1. 1 supports tool calling. The catalogue re-syncs hourly, so a newly released model shows up here on its own.