opendunes

Llama 3.2 3B Instruct

by MetaReleased 25 September 2024

Llama 3.2 3B Instruct is a small multilingual text model from Meta, covering eight languages (English, Spanish and Hindi among them) and reading about 131 pages at once. It is tuned for following instructions, thinking things through and using tools. Use it for chat, summaries and light automated steps at small scale.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,073 DA per message3 000 DA buys about 41 000 messages

One message, the ordinary use

1 000 tokens sent× 16,94 DA per 1M0,017 DA
500 tokens back× 111,50 DA per 1M0,056 DA
Total≈ 0,073 DA

Every rate

Meter↑ you send↓ comes back
Text tokens16,94 DA111,50 DA

per 1M tokens

Summarise a customer review≈ 0,013 DA
Extract fields from an order email≈ 0,017 DA
Answer a quick question≈ 0,030 DA
Reply to a customer email≈ 0,055 DA
Translate a full page of text≈ 0,10 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

Two companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Parasail…
↑ Sent, per 1M
16,64 DA
↓ Back, per 1M
109,84 DA
Latency
…
Throughput
…
Cloudflare…
↑ Sent, per 1M
16,94 DA
↓ Back, per 1M
111,50 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackLatencyThroughputUptime
Parasail16,64 DA109,84 DA………
Cloudflare16,94 DA111,50 DA………

You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
meta-llama/llama-3.2-3b-instruct
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="meta-llama/llama-3.2-3b-instruct",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Structured output

Get JSON you can parse instead of prose.

structured_outputs

Questions about Llama 3.2 3B Instruct

  • How much does Llama 3.2 3B Instruct cost in dinars?

    About 0,073 DA per message. ↑ 16,94 DA · ↓ 111,50 DA per 1M tokens.

  • Is Llama 3.2 3B Instruct free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Llama 3.2 3B Instruct best for?

    Llama 3.2 3B Instruct is a small multilingual text model from Meta, covering eight languages (English, Spanish and Hindi among them) and reading about 131 pages at once. It is tuned for following instructions, thinking things through and using tools. Use it for chat, summaries and light automated steps at small scale.

  • Llama 3.2 3B Instruct or Llama 3.2 1B Instruct?

    Llama 3.2 1B Instruct costs 0,031 DA less for the same message.

  • How do I pay for Llama 3.2 3B Instruct without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Llama 3.2 3B Instruct included, is paid from that balance. No foreign card, no conversion.

  • Does Llama 3.2 3B Instruct work in Arabic, French or Darja?

    Meta supports 8 languages: English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. Arabic and Darja are not named.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 54 000 words at once.

  • Is Llama 3.2 3B Instruct open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Llama 3.2 3B Instruct, and when was it released?

    Meta. Released 25 September 2024. It knows the world up to 31 December 2023.

Other Meta models, priced in dinars

See all Meta models
Llama 3.1 8B InstructMeta · Jul 23, 2024

Llama 3.1 8B Instruct is the small model of Meta's Llama 3.1 family, tuned to follow instructions and described as fast and efficient. You send text and get text back; it reads about 131 pages at once and can use tools or fill in an exact form you give it. Use it for sorting, short rewrites, simple chat and high-volume jobs.

Uses your tools130 pages at onceOpen weights
≈0,030 DAper message
View model
Llama 3.3 70B InstructMeta · Dec 6, 2024

Llama 3.3 70B Instruct is a text-only Meta model tuned for conversation in English, Spanish, French, German, Italian, Portuguese, Hindi and Thai. You send a chat, with tools or an exact form to fill in if you need them, and get a reply of up to about 16 pages from a conversation of up to 131 pages. Pick it for assistants and support in those languages.

Uses your tools130 pages at onceOpen weights
≈0,33 DAper message
View model
Llama 4 ScoutMeta · Apr 5, 2025

Llama 4 Scout takes text and pictures and answers in text or code across 12 languages. It reads about 1,300 pages at once, enough to caption or question many images, or take in a very large document in one request. Meta tuned it for chat in many languages, captions and image understanding.

Uses your tools1 300 pages at onceOpen weights
≈0,083 DAper message
View model
Llama 4 MaverickMeta · Apr 5, 2025

Llama 4 Maverick takes text and pictures and answers in text or code across 12 languages, keeping about a thousand pages of conversation in mind. Meta tuned it for reasoning about images and for assistant-style chat. Use it to answer questions about photos, charts and screenshots, or for multilingual assistants with long conversations.

Uses your tools520 pages at onceOpen weights
≈0,28 DAper message
View model