Body Builder (beta) API pricing in toman

Body Builder (beta) example: sentiment of a customer review

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

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="openrouter/bodybuilder",
    messages=[{"role": "user", "content": "Give the sentiment (positive/negative/neutral) and the reason: \"Arrived fast but the box was crushed.\""}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

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

const stream = await client.chat.completions.create({
  model: "openrouter/bodybuilder",
  messages: [{ role: "user", content: "Give the sentiment (positive/negative/neutral) and the reason: \"Arrived fast but the box was crushed.\"" }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openrouter/bodybuilder",
    "messages": [{"role": "user", "content": "Give the sentiment (positive/negative/neutral) and the reason: \"Arrived fast but the box was crushed.\""}],
    "stream": true
  }'

What is Body Builder (beta) good for?

Body Builder (beta) comes from OpenRouter; in uttapen you reach it with the model id "openrouter/bodybuilder". It accepts up to 128,000 tokens of input per call, so a long document or several source files fit in a single request. It has no fixed price: the destination model is chosen per request, and you are charged exactly what the model that answered actually cost.

Body Builder (beta) is text in, text out: no tool calling, no image input. For chat, rewriting, translation and summarising that is all you need, and it costs less than a model carrying features you never call.

Its nearest relative in the catalogue is "openrouter/fusion", and choosing between those two is where most people hesitate. The context windows differ too: 128,000 against 1,000,000 tokens.

OpenRouter has 6 models in our catalogue. It does not support include_reasoning, max_tokens, reasoning, response_format, 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.

What to use it for: automatic routing when you would rather not pick a model yourself.

Provider's own description

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

Frequently asked

How do I call Body Builder (beta) 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 "openrouter/bodybuilder". Nothing else in your code changes.

What does Body Builder (beta) cost in toman?

This model has no fixed price: the cost depends on the model that answered the request, and that exact amount is what leaves your wallet.

How much input does Body Builder (beta) take?

Up to 128,000 tokens per request, roughly 96k words. Cap the answer length yourself with max_tokens.

Can I stream Body Builder (beta)'s output?

Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.