Llama 3.1 405B (Hyp)
Largest dense Llama. Used as a quality benchmark for open weights, heavy to run, often hosted via Together / DeepInfra / Cerebras.
Llama 3.1 405B (Hyp) is a frontier AI model from Hyperbolic. It costs $4.000 per million input tokens and $4.000 per million output tokens (blended $4.000/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 Hyperbolic
See all 4 →Frequently asked questions
How much does Llama 3.1 405B (Hyp) cost?
Llama 3.1 405B (Hyp) costs $4.000 per million input tokens and $4.000 per million output tokens, for a blended reference rate of $4.000 per million tokens.
What is Llama 3.1 405B (Hyp)'s context window?
Llama 3.1 405B (Hyp) supports up to 128,000 tokens of context in a single request.
What is Llama 3.1 405B (Hyp) best for?
Llama 3.1 405B (Hyp) is well suited to Top open-weights quality, Permissive license and Strong reasoning.
Who makes Llama 3.1 405B (Hyp)?
Llama 3.1 405B (Hyp) is developed and served by Hyperbolic.