Create an API key

Llama 3.1 70B Instruct API: toman pricing and code

meta-llama/llama-3.1-70b-instruct

Create a keyTry it
Input · per 1M tokens
249,278 toman
Output · per 1M tokens
249,278 toman
One 1,000-word request ≈
648 toman

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

Llama 3.1 70B Instruct example: translation between Persian and English

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-3.1-70b-instruct",
    messages=[{"role": "user", "content": "Translate into fluent Persian: \"Your order is confirmed and ships within 48 hours.\""}],
    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: "meta-llama/llama-3.1-70b-instruct",
  messages: [{ role: "user", content: "Translate into fluent Persian: \"Your order is confirmed and ships within 48 hours.\"" }],
  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": "meta-llama/llama-3.1-70b-instruct",
    "messages": [{"role": "user", "content": "Translate into fluent Persian: \"Your order is confirmed and ships within 48 hours.\""}],
    "stream": true
  }'

What is Llama 3.1 70B Instruct good for?

The id for Llama 3.1 70B Instruct in our API is "meta-llama/llama-3.1-70b-instruct", served from Meta Llama. Context is 131,072 tokens; past that you have to summarise the history yourself. A single response can run to 8,192 tokens. On price it sits in the "cheap" band — cheaper than 277 and dearer than 121 of the other paid models in the catalogue.

Llama 3.1 70B Instruct 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.

For a back-of-envelope figure: about 648 toman per 1,000-word exchange (249,278 in, 249,278 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 Weaver (alpha): Llama 3.1 70B Instruct works out about 30% more expensive, 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 154 thousand-word requests on Llama 3.1 70B Instruct, and every 1,000 toman is about 1,543 words of round trip. A job with one million input tokens and one million output tokens comes to 498,556 toman in total. Filling this model's 131,072-token window costs 32,673 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-3.2-1b-instruct", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 6.3× more expensive (648 against 103 toman). The context windows differ too: 131,072 against 60,000 tokens. Maximum answer length differs as well: 8,192 against 54,000 tokens. On parameters the other takes frequency_penalty, logit_bias, min_p, presence_penalty.

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 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 Aion-2.0 at 131,072 tokens.

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

Provider's own description

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

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 out474 toman
Summarising a ten-page document4,000 in + 600 out1,147 toman
Classifying a thousand short rows120,000 in + 20,000 out34,899 toman

Price history

DateInput (toman/1M)Output (toman/1M)
4 Nov 2026249,278249,278
21 Sep 2026138,488138,488
21 Sep 2026249,278249,278
12 Sep 2026138,488138,488
12 Sep 2026249,278249,278
11 Sep 2026138,488138,488
11 Sep 2026249,278249,278
7 Sep 2026138,488138,488

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

Frequently asked

How do I call Llama 3.1 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-3.1-70b-instruct". Nothing else in your code changes.
What does Llama 3.1 70B Instruct cost in toman?
249,278 toman per 1M input tokens and 249,278 toman per 1M output tokens; a 1,000-word request is around 648 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Llama 3.1 70B Instruct take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 8,192 tokens.
Can I stream Llama 3.1 70B 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.