Reflection models, priced in toman
1 Reflection models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Reflection on uttapen
Reflection 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 Reflection model here is Beam 1.0 501B A23B: roughly 563 toman for a 1,000-word request.
On capabilities: 1 supports tool calling, 1 does multi-step reasoning. The longest context belongs to Beam 1.0 501B A23B, at 1,048,576 tokens.
Every Reflection 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 Reflection model should I start with?
Every Reflection model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | Tool callingReasoningJSON output | 1,048,576 | 86,555 | 346,219 |
Common questions about the Reflection API
- How do I reach the Reflection 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 Reflection model id. No international card, no VPN. - What do Reflection models cost in toman?
- It depends on the model: the cheapest, Beam 1.0 501B A23B, is about 563 toman for a 1,000-word request, and the dearest, Beam 1.0 501B A23B, about 563 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Reflection 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.