Llama-3.1-405B (Cerebras)
Largest dense Llama. Used as a quality benchmark for open weights, heavy to run, often hosted via Together / DeepInfra / Cerebras.
Llama-3.1-405B (Cerebras) is a frontier AI model from Cerebras. It costs $0.990 per million input tokens and $0.990 per million output tokens (blended $0.990/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 Cerebras
See all 4 →Frequently asked questions
How much does Llama-3.1-405B (Cerebras) cost?
Llama-3.1-405B (Cerebras) costs $0.990 per million input tokens and $0.990 per million output tokens, for a blended reference rate of $0.990 per million tokens.
What is Llama-3.1-405B (Cerebras)'s context window?
Llama-3.1-405B (Cerebras) supports up to 128,000 tokens of context in a single request.
What is Llama-3.1-405B (Cerebras) best for?
Llama-3.1-405B (Cerebras) is well suited to Top open-weights quality, Permissive license and Strong reasoning.
Who makes Llama-3.1-405B (Cerebras)?
Llama-3.1-405B (Cerebras) is developed and served by Cerebras.