Llama 3.1 405B

im/together-llama-3.1-405b

stable

Meta's largest open-weights model. Top-tier reasoning and knowledge.

Specs

Capabilities and limits

Provider: Together AI
Model family: llama-3.1
Type: chat
Context length: 131,072 tokens
Max output: 8,192 tokens
Streaming: Yes
Tool calling: Yes
JSON mode: Yes
Vision: No

Pricing

Active credit rate

Input: 4400000 cr / M tokens · $4.4000
Output: 4400000 cr / M tokens · $4.4000
Effective from: 5/17/2026

Best for

reasoningknowledgelong-contextcoding

Endpoints

Routes this model serves

/v1/chat/completions