AI Agent Hub
Back to models
🤖

Meta: Llama 3.3 70B Instruct

Closed Source meta-llama
8.4 / 10 131.1K context Proprietary

About this model

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...

Benchmark Scores

MATH
77.0
MBPP
87.6
HumanEval
88.4

Technical Specs

  • Architecture: text->text
  • Context Window: 131,072 tokens
  • Input Modalities: text

Hardware Requirements

  • API-only (no local hardware needed)

Pricing

Input Output Currency
0.71 / 1M tokens 0.71 / 1M tokens USD