Meta Models
Meta logo

Meta: Llama 3.3 70B Instruct

70B

byMeta

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...

Input Price$0.58/1M tokens
Output Price$0.71/1M tokens
Intelligence8.6
Coding10.7

Specifications

Technical details and pricing.

ProviderMeta
Context Window131,072 tokens
Release DateDec 6, 2024
ModalitiesText
CapabilitiesFunction Calling, Structured Outputs, JSON Mode

Benchmarks

12 benchmark scores from Artificial Analysis.

GPQA49.8%
MMLU Pro71.3%
HLE4.0%
LiveCodeBench28.8%
MATH 50077.3%
AIME 20257.7%
AIME30.0%
SciCode26.0%
LCR15.0%
IFBench47.1%
Tau226.6%
TerminalBench Hard3.0%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Meta: Llama 3.3 70B Instruct good for?

Use Meta: Llama 3.3 70B Instruct for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Meta: Llama 3.3 70B Instruct cost?

Pricing is based on usage. Current rates are $0.58/1M tokens for input and $0.71/1M tokens for output.

Can I try Meta: Llama 3.3 70B Instruct for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Meta: Llama 3.3 70B Instruct support images or audio?

Meta: Llama 3.3 70B Instruct focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.