Create an API key

Llama 4 Maverick API: toman pricing and code

meta-llama/llama-4-maverick

Image inputTool callingJSON output
Create a keyTry it
Input · per 1M tokens
121,177 toman
Output · per 1M tokens
346,219 toman
One 1,000-word request ≈
608 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 58,857 toman per 1M tokens.Pricing and top-ups

Llama 4 Maverick example: reading an image into JSON

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

# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Return only the invoice number and the total, as JSON."},
        {"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
      ]
    }]
  }'
import base64, json
from openai import OpenAI

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

img = base64.b64encode(open("factor.jpg", "rb").read()).decode()

resp = client.chat.completions.create(
    model="meta-llama/llama-4-maverick",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
        ],
    }],
    response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))
import OpenAI from "openai";
import { readFileSync } from "node:fs";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");

const resp = await client.chat.completions.create({
  model: "meta-llama/llama-4-maverick",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Return the invoice number, the date and the total as JSON." },
      { type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
    ],
  }],
  response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));

What is Llama 4 Maverick good for?

The id for Llama 4 Maverick in our API is "meta-llama/llama-4-maverick", served from Meta Llama. Context is 524,288 tokens; past that you have to summarise the history yourself. A single response can run to 32,768 tokens. On price it sits in the "cheap" band — cheaper than 249 and dearer than 141 of the other paid models in the catalogue.

Capabilities available on this id: it reads images directly, which makes it a real option for invoices, forms and screenshots; 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.

For a back-of-envelope figure: about 608 toman per 1,000-word exchange (121,177 in, 346,219 out, per 1M tokens). It supports cached input: repeated context is billed at 58,857 toman per 1M, which matters a lot if your system prompt is long. 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 Qwen3 VL 30B A3B Thinking, and Llama 4 Maverick costs about the same, and its context window is larger. 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 164 thousand-word requests on Llama 4 Maverick, and every 1,000 toman is about 1,645 words of round trip. A job with one million input tokens and one million output tokens comes to 467,396 toman in total. Filling this model's 524,288-token window costs 63,532 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "meta-llama/llama-4-scout", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 3.4× more expensive (608 against 180 toman). The context windows differ too: 524,288 against 327,680 tokens. Maximum answer length differs as well: 32,768 against 16,384 tokens. On parameters, this one takes logprobs, response_format, top_logprobs while the other takes min_p.

Meta Llama has 8 models in our catalogue; the cheapest is Llama 3.1 8B Instruct at 59 toman per thousand words and the dearest Llama 3.1 70B Instruct at 648. Among the less common parameters it accepts logit_bias, logprobs, presence_penalty, repetition_penalty, top_k, 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 Inkling at 524,288 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, pulling text and fields out of images, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.

Provider's own description

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

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 out320 toman
Summarising a ten-page document4,000 in + 600 out692 toman
Classifying a thousand short rows120,000 in + 20,000 out21,466 toman

Price history

DateInput (toman/1M)Output (toman/1M)
5 Nov 2026121,177346,219
6 Oct 202664,916225,908
22 Sep 202664,916225,908
21 Sep 202669,244276,975
14 Sep 202664,916225,908
7 Sep 202669,244240,969

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call Llama 4 Maverick 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-4-maverick". Nothing else in your code changes.
What does Llama 4 Maverick cost in toman?
121,177 toman per 1M input tokens and 346,219 toman per 1M output tokens; a 1,000-word request is around 608 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Llama 4 Maverick take?
Up to 524,288 tokens per request, roughly 393k words. A single answer can reach 32,768 tokens.
Does Llama 4 Maverick support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.