Create an API key

GPT Audio API: toman pricing and code

openai/gpt-audio

Tool callingJSON outputAudio input
Create a keyTry it
Input · per 1M tokens
865,548 toman
Output · per 1M tokens
3,462,194 toman
One 1,000-word request ≈
5,626 toman

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

GPT Audio 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-audio", 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-audio", messages=messages, tools=tools)
print(final.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

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

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

const args = JSON.parse(call.function.arguments);
const result = { sku: args.sku, qty: 7 };

messages.push(first.choices[0].message, { role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
const final = await client.chat.completions.create({ model: "openai/gpt-audio", messages, tools });
console.log(final.choices[0].message.content);
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "messages": [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "check_stock",
        "parameters": {"type": "object", "properties": {"sku": {"type": "string"}}, "required": ["sku"]}
      }
    }]
  }'

What is GPT Audio good for?

The id for GPT Audio in our API is "openai/gpt-audio", served from OpenAI. Context is 128,000 tokens; past that you have to summarise the history yourself. A single response can run to 16,384 tokens. On price it sits in the "mid-range" band — cheaper than 53 and dearer than 319 of the other paid models in the catalogue.

What it can do beyond plain text: it accepts audio input; 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 865,548 toman per 1M input tokens and 3,462,194 per 1M output tokens. A 1,000-word round trip on GPT Audio lands near 5,626 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), and GPT Audio costs about the same, and its context window is the same size. 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 18 thousand-word requests on GPT Audio, and every 1,000 toman is about 178 words of round trip. A job with one million input tokens and one million output tokens comes to 4,327,742 toman in total. Filling this model's 128,000-token window costs 110,790 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-audio-mini", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 4.2× more expensive (5,626 against 1,350 toman).

OpenAI has 81 models in our catalogue; the cheapest is gpt-oss-20b (batch) at 61 toman per thousand words and the dearest GPT-5.5 Pro at 94,518. Among the less common parameters it accepts logit_bias, logprobs, presence_penalty, 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 Nova Micro 1.0 at 128,000 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

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 out2,683 toman
Summarising a ten-page document4,000 in + 600 out5,540 toman
Classifying a thousand short rows120,000 in + 20,000 out173,110 toman

Frequently asked

How do I call GPT Audio 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-audio". Nothing else in your code changes.
What does GPT Audio cost in toman?
865,548 toman per 1M input tokens and 3,462,194 toman per 1M output tokens; a 1,000-word request is around 5,626 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GPT Audio take?
Up to 128,000 tokens per request, roughly 96k words. A single answer can reach 16,384 tokens.
Does GPT Audio 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.