How much does Llama 3.2 3B Instruct cost?

Llama 3.2 3B Instruct is free to use on Hormouz. There is no charge for input or output tokens. Current rates are always shown in the Hormouz dashboard.

How do I access Llama 3.2 3B Instruct from inside Iran?

Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Llama 3.2 3B Instruct from inside Iran, with no foreign credit card or circumvention tooling required.

Is Llama 3.2 3B Instruct compatible with OpenAI code?

Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing OpenAI SDKs and code run without a rewrite.

Is Llama 3.2 3B Instruct multilingual?

Yes. It supports eight languages out of the box and is tuned for dialogue, reasoning and summarisation. At 3B parameters with a 131K-token context, it is fast and cheap, which suits high-volume chat and prototyping.

Meta: Llama 3.2 3B Instruct: AI model

Meta Llama 3.2 3B Instruct is a compact multilingual model for dialogue, reasoning and summarisation, with a 131K context. Free to use through Hormouz from inside Iran.

Context window:: 131,072 tokens
Input:: $0.05/1M tokens
Output:: $0.33/1M tokens
Type:: text

Streaming
Long context

Llama 3.2 3B Instruct is a 3-billion-parameter multilingual model from Meta, optimised for dialogue generation, reasoning and summarisation. It supports eight languages out of the box and was trained on a very large token corpus, giving it solid instruction-following and tool-use for its size.

At just 3B parameters it is fast and cheap to run, which makes it a good fit for high-volume chat, on-device-style workloads and prototyping. Its 131K-token context lets it work over longer inputs than its small size would suggest.

Llama 3.2 3B Instruct is free to use through Hormouz. You pay nothing for input or output tokens. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.2-3b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Meta
Type	Text
Context window	131,072 tokens
Pricing	$0.05/M in · $0.33/M out
API	Chat Completions
Capabilities	Streaming

Sizes in this family

Size	Context window	Pricing
1B	60,000	$0.03/M in · $0.20/M out
3B	131,072	$0.05/M in · $0.33/M out

Benchmarks

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

25.5%

HLE

Humanity's Last Exam

5.3%

IFBench

Instruction-following

26.2%

AA-LCR

Long-context reasoning

4.3%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

21.1%

Source: Artificial Analysis

Code example

cURL

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.2-3b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="meta-llama/llama-3.2-3b-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "meta-llama/llama-3.2-3b-instruct",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Meta: Llama 3.2 3B Instruct API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Meta: Llama 3.2 3B Instruct and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Llama 3.2 3B Instruct cost?: Llama 3.2 3B Instruct is free to use on Hormouz. There is no charge for input or output tokens. Current rates are always shown in the Hormouz dashboard.
How do I access Llama 3.2 3B Instruct from inside Iran?: Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Llama 3.2 3B Instruct from inside Iran, with no foreign credit card or circumvention tooling required.
Is Llama 3.2 3B Instruct compatible with OpenAI code?: Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing OpenAI SDKs and code run without a rewrite.
Is Llama 3.2 3B Instruct multilingual?: Yes. It supports eight languages out of the box and is tuned for dialogue, reasoning and summarisation. At 3B parameters with a 131K-token context, it is fast and cheap, which suits high-volume chat and prototyping.

Updated 2026-10-13