Relace models, priced in toman
2 Relace models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Relace on uttapen
Relace currently has 2 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Relace alone is wide: Relace Apply 3 runs about 945 toman for a 1,000-word request, while Relace Search costs 1,800 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Relace output price undercuts about 37% of the other paid models.
On capabilities: 1 supports tool calling. The longest context belongs to Relace Apply 3, at 256,000 tokens.
Every Relace 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 Relace model should I start with?
Every Relace model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Relace Apply 3relace/relace-apply-3 | 256,000 | 294,286 | 432,774 | |
Relace Searchrelace/relace-search | Tool callingJSON output | 256,000 | 346,219 | 1,038,658 |
Common questions about the Relace API
- How do I reach the Relace 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 Relace model id. No international card, no VPN. - What do Relace models cost in toman?
- It depends on the model: the cheapest, Relace Apply 3, is about 945 toman for a 1,000-word request, and the dearest, Relace Search, about 1,800 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Relace models are on uttapen?
- 2. 1 supports tool calling. The catalogue re-syncs hourly, so a newly released model shows up here on its own.