Llama 3.1 405B (Together)
Largest dense Llama. Used as a quality benchmark for open weights, heavy to run, often hosted via Together / DeepInfra / Cerebras.
Llama 3.1 405B (Together) is a frontier AI model from Together AI. It costs $3.500 per million input tokens and $3.500 per million output tokens (blended $3.500/M), with a 128,000-token context window.
Profile inherited from upstream Llama 3.1 405B ↗ — this is a hosted variant of the same open-weights model.
- Top open-weights quality
- Permissive license
- Strong reasoning
- Open-weights quality ceiling
- Synthetic data generation
- Distillation source
Benchmarks
More from Together AI
See all 10 →Frequently asked questions
How much does Llama 3.1 405B (Together) cost?
Llama 3.1 405B (Together) costs $3.500 per million input tokens and $3.500 per million output tokens, for a blended reference rate of $3.500 per million tokens.
What is Llama 3.1 405B (Together)'s context window?
Llama 3.1 405B (Together) supports up to 128,000 tokens of context in a single request.
What is Llama 3.1 405B (Together) best for?
Llama 3.1 405B (Together) is well suited to Top open-weights quality, Permissive license and Strong reasoning.
Who makes Llama 3.1 405B (Together)?
Llama 3.1 405B (Together) is developed and served by Together AI.