Meta · Open weights

Llama 3.3 70B

Llama 3.3 70B costs $0.3809 per million input tokens and $2.9289 per million output tokens on Roar AI. Meta’s dependable mid-size open model, close to Llama 3.1 405B at a sixth of the size.

Input$0.3809per 1M tokens

Output$2.9289per 1M tokens

BillingOne monthly invoiceevery model on one key

Get started See every model’s rate

About Llama 3.3 70B

Llama 3.3 70B was Meta’s answer to an expensive problem: it comes close to the much larger Llama 3.1 405B on key tests at about a sixth of the size. It is a plain, predictable model — no reasoning step, so answers start quickly — that follows instructions very well (92.1% on IFEval) and writes clean code for its class (88.4% on HumanEval).

It has been around since December 2024, so it is well understood and widely tested. That makes it a steady choice for drafting, summarising and answering from your own documents, where consistent behaviour matters more than the newest benchmark score.

What is Llama 3.3 70B good for?

Drafting and editing.
Answering questions from your own documents.
Assistants that need fast, predictable replies.

Where to be careful

Its knowledge stops at December 2023.
No reasoning mode: far behind 2026 reasoning models on hard science and maths (50.5% on GPQA Diamond).
Text only, under Meta’s own licence.

Price

Input$0.3809 per 1M tokens

Output$2.9289 per 1M tokens

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $4.07 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 19 October 2026.

Specs

Made byMeta

ReleasedDecember 2024

TypeChat

Context window128K tokens

ReadsText

Thinks before answeringNo

WeightsOpen (Llama 3.3 Community License)

Size70B, dense

Processed inGlobal

Model idllama-3.3-70b

Call it

Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Compare Llama 3.3 70B

Llama 3.3 70B vs gpt-oss-120bHead to headMiniMax-M3Similar priceQwen 3.8 27BSimilar priceQwen 3.8 27B (Colombo)Similar price

Questions

How much does Llama 3.3 70B cost?

Input is $0.3809 per 1M tokens; output is $2.9289 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $4.07. The rate is published and does not change from one request to the next.

Can I use Llama 3.3 70B alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Llama 3.3 70B to another model is a change to one word in your code.

Is Llama 3.3 70B open source?

Its weights are open under the Llama 3.3 Community License licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

Try Llama 3.3 70B
on one key

Get started Read the docs