Perceptron models, priced in toman
2 Perceptron models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Perceptron on uttapen
Perceptron 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 Perceptron alone is wide: Perceptron Mk1 runs about 743 toman for a 1,000-word request, while Perceptron Mk1.5 costs 743 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 Perceptron output price undercuts about 53% of the other paid models.
On capabilities: 2 take image input, 1 supports tool calling, 2 do multi-step reasoning, 1 accepts audio. The longest context belongs to Perceptron Mk1.5, at 36,864 tokens.
Every Perceptron 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 Perceptron model should I start with?
Every Perceptron model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Perceptron Mk1perceptron/perceptron-mk1 | Image inputReasoningJSON output | 32,768 | 51,933 | 519,329 |
Perceptron Mk1.5perceptron/perceptron-mk1.5 | Image inputTool callingReasoningJSON output | 36,864 | 51,933 | 519,329 |
Common questions about the Perceptron API
- How do I reach the Perceptron 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 Perceptron model id. No international card, no VPN. - What do Perceptron models cost in toman?
- It depends on the model: the cheapest, Perceptron Mk1, is about 743 toman for a 1,000-word request, and the dearest, Perceptron Mk1.5, about 743 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Perceptron models are on uttapen?
- 2. 1 supports tool calling and 2 accept image input. The catalogue re-syncs hourly, so a newly released model shows up here on its own.