llama-3.3-70b

by Llama

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.

API Pricing

Input	$0.6 / 1M tokens
Output	$0.6 / 1M tokens

Specifications

Context window

65,536 tokens

Use llama-3.3-70b via the AIHubMix unified API — one interface for every major LLM.