uttapen

One endpoint for 400+ language models, billed in toman

Change base_url and nothing else. Toman wallet, API keys, real streaming, models from OpenAI, Anthropic, Google and DeepSeek.

Payment
Toman · no foreign card
Compatibility
OpenAI SDK
Top-up from
50,000 toman
The only line that changeshttps://api.uttapen.ir/v1
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

The same code works with stream=True, tools and response_format with no further changes.

Models people actually use

Price per 1M tokens in toman, at today's rate.

All models →

430 models from 51 providers, every one priced in toman.

Three steps to your first request

  1. 1

    Sign up with a mobile number

    An SMS code. No email, no international card.

  2. 2

    Top up the toman wallet

    A local payment gateway, with an official invoice for every top-up.

  3. 3

    Create a key and change base_url

    The official OpenAI SDK; the rest of your code stays as it is.

You pay for the tokens you used
Every request is billed against the usage it actually reported. A failed request costs nothing, and every line is visible in your usage panel.
Prompts and answers are never stored
Only metadata: model, tokens, cost, timing. The text of an API request never reaches a log or a database.
Servers in Iran, models abroad
Panel, wallet and keys run inside Iran; model calls leave over a private route. No VPN, no foreign card.

Ready?

Sign up with a phone number, top up from 50,000 toman, key in 30 seconds.