uttapen
Create an API key

GPT-4 API: toman pricing and code

openai/gpt-4

toolsjson
Create a keyTry it
Input · per 1M tokens
8,703,750 toman
Output · per 1M tokens
17,407,500 toman
One 1,000-word request ≈
33,945 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

GPT-4 example: tool calling

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="openai/gpt-4", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="openai/gpt-4", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is GPT-4 good for?

GPT-4 comes from OpenAI; in uttapen you reach it with the model id "openai/gpt-4". It accepts up to 8,191 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 4,096 tokens. On price it sits in the "expensive" band — cheaper than 392 and dearer than 14 of the other paid models in the catalogue.

What it can do beyond plain text: it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Pricing is 8,703,750 toman per 1M input tokens and 17,407,500 per 1M output tokens. A 1,000-word round trip on GPT-4 lands near 33,945 toman. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is Command R+ (08-2024): GPT-4 works out roughly 7.2× more expensive, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 3 thousand-word requests on GPT-4, and every 1,000 toman is about 29 words of round trip. A job with one million input tokens and one million output tokens comes to 26,111,250 toman in total. Filling this model's 8,191-token window costs 71,292 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "openai/gpt-3.5-turbo-0613", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 30× dearer (33,945 against 1,131 toman). The context windows differ too: 8,191 against 4,095 tokens. Maximum answer length differs as well: 4,096 against 3,685 tokens. On parameters, this one takes max_tokens.

OpenAI has 95 models in our catalogue; the cheapest is gpt-oss-20b at 60 toman per thousand words and the dearest o1-pro at 282,872. Among the less common parameters it accepts logit_bias, logprobs, max_completion_tokens, top_logprobs — all through the standard request body. It does not support include_reasoning, reasoning, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is R1 Distill Llama 70B at 8,192 tokens.

Good fits: work where the quality of the answer matters more than its cost, agents that reach out to APIs and databases, extracting data against a fixed schema, short single-turn requests (the context window is small).

Provider's own description

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out20,019 toman
Summarising a ten-page document4,000 in + 600 out45,260 toman
Classifying a thousand short rows120,000 in + 20,000 out1,392,600 toman

Frequently asked

How do I call GPT-4 from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "openai/gpt-4". Nothing else in your code changes.
What does GPT-4 cost in toman?
8,703,750 toman per 1M input tokens and 17,407,500 toman per 1M output tokens; a 1,000-word request is around 33,945 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GPT-4 take?
Up to 8,191 tokens per request, roughly 6k words. A single answer can reach 4,096 tokens.
Does GPT-4 support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.