uttapen
Create an API key

Llama 3.2 1B Instruct API: toman pricing and code

meta-llama/llama-3.2-1b-instruct

Create a keyTry it
Input · per 1M tokens
7,833 toman
Output · per 1M tokens
58,315 toman
One 1,000-word request ≈
86 toman

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

Llama 3.2 1B Instruct example: writing product copy

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="meta-llama/llama-3.2-1b-instruct",
    messages=[{"role": "user", "content": "Write a 40-word product description for a 1.7-litre stainless steel electric kettle."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

What is Llama 3.2 1B Instruct good for?

Meta publishes this model; we expose it under the id "meta-llama/llama-3.2-1b-instruct". Its context window is 60,000 tokens, roughly 45k English words in one request. A single response can run to 54,000 tokens. On price it sits in the "very cheap" band — cheaper than 47 and dearer than 359 of the other paid models in the catalogue.

This one handles text only. If you need function calling or image understanding, pick another model from the same catalogue — swapping is a one-line change.

For a back-of-envelope figure: about 86 toman per 1,000-word exchange (7,833 in, 58,315 out, per 1M tokens). 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 gpt-oss-20b (batch): Llama 3.2 1B Instruct works out roughly 1.1× cheaper, 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 1,163 thousand-word requests on Llama 3.2 1B Instruct, and every 1,000 toman is about 11,628 words of round trip. A job with one million input tokens and one million output tokens comes to 66,149 toman in total. Filling this model's 60,000-token window costs 470 toman on the input side alone, which is the real reason to keep conversation history short.

Meta has 8 models in our catalogue; the cheapest is Llama 3.1 8B Instruct at 49 toman per thousand words and the dearest Llama 4 Maverick at 338. Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. It does not support include_reasoning, reasoning, response_format, tool_choice, 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 at 64,000 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising.

Provider's own description

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

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 out35 toman
Summarising a ten-page document4,000 in + 600 out66 toman
Classifying a thousand short rows120,000 in + 20,000 out2,106 toman

Frequently asked

How do I call Llama 3.2 1B Instruct 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 "meta-llama/llama-3.2-1b-instruct". Nothing else in your code changes.
What does Llama 3.2 1B Instruct cost in toman?
7,833 toman per 1M input tokens and 58,315 toman per 1M output tokens; a 1,000-word request is around 86 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Llama 3.2 1B Instruct take?
Up to 60,000 tokens per request, roughly 45k words. A single answer can reach 54,000 tokens.
Can I stream Llama 3.2 1B Instruct'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.