Llama 3.1 405B

meta

Meta's Llama 3.1 405B base pre-trained model. It has demonstrated strong performance compared to leading closed-source models in human evaluations. Usage of this model is subject to Meta's Acceptable Use Policy.

Try Now

Example Use Cases

Base model for fine-tuning

Raw text completion without instruction tuning

Largest open-source llama

Technical Specifications

Context Window

32,768 tokens

Max Output

32,768 tokens

Cache Miss Cost

$4 per 1M tokens

Non-Reasoning Cost

$4 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus