Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

About Meta: Llama 3.3 70B Instruct

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 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.

Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Model Card

Specifications

Context Length

131,072

Tokenizer

Llama3

Pricing

Prompt

0.120

Completion

0.300

Image

0

Request

0

Last updated: 4/11/2025