Create an API key

Llama 3.3 70B Instruct API: toman pricing and code

meta-llama/llama-3.3-70b-instruct

Tool callingJSON output
Create a keyTry it
Input · per 1M tokens
69,244 toman
Output · per 1M tokens
180,034 toman
One 1,000-word request ≈
324 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 34,622 toman per 1M tokens.Pricing and top-ups

Llama 3.3 70B Instruct 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="meta-llama/llama-3.3-70b-instruct", 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="meta-llama/llama-3.3-70b-instruct", 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: "meta-llama/llama-3.3-70b-instruct", 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: "meta-llama/llama-3.3-70b-instruct", 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": "meta-llama/llama-3.3-70b-instruct",
    "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 Llama 3.3 70B Instruct good for?

Llama 3.3 70B Instruct comes from Meta Llama; in uttapen you reach it with the model id "meta-llama/llama-3.3-70b-instruct". It accepts up to 131,072 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 128,000 tokens. On price it sits in the "very cheap" band — cheaper than 299 and dearer than 99 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 69,244 toman per 1M input tokens and 180,034 per 1M output tokens. A 1,000-word round trip on Llama 3.3 70B Instruct lands near 324 toman. It supports cached input: repeated context is billed at 34,622 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 Hy3: Llama 3.3 70B Instruct works out about 10% 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 309 thousand-word requests on Llama 3.3 70B Instruct, and every 1,000 toman is about 3,086 words of round trip. A job with one million input tokens and one million output tokens comes to 249,278 toman in total. Filling this model's 131,072-token window costs 9,076 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-3.1-8b-instruct", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 5.5× more expensive (324 against 59 toman). Maximum answer length differs as well: 128,000 against 117,964 tokens.

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, min_p, presence_penalty, repetition_penalty, top_k — 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 Aion-2.0 at 131,072 tokens.

Good fits: high-volume work such as classification, tagging and bulk summarising, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

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 out176 toman
Summarising a ten-page document4,000 in + 600 out385 toman
Classifying a thousand short rows120,000 in + 20,000 out11,910 toman

Price history

DateInput (toman/1M)Output (toman/1M)
5 Nov 202669,244180,034
16 Oct 202634,622110,790
13 Oct 2026204,269273,513
9 Oct 202676,168173,110
8 Oct 202634,622110,790
5 Oct 202676,168173,110
5 Oct 202634,622110,790
4 Oct 202676,168173,110
7 Sep 202634,622110,790

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

Frequently asked

How do I call Llama 3.3 70B 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-3.3-70b-instruct". Nothing else in your code changes.
What does Llama 3.3 70B Instruct cost in toman?
69,244 toman per 1M input tokens and 180,034 toman per 1M output tokens; a 1,000-word request is around 324 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Llama 3.3 70B Instruct take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 128,000 tokens.
Does Llama 3.3 70B Instruct 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.