Llama 3.1 70B (Anyscale)
The 2024 70B Llama that defined the open-weights chat baseline before Llama 3.3. Still common where hosts haven't upgraded yet.
Llama 3.1 70B (Anyscale) is a efficient AI model from Anyscale. It costs $1.00 per million input tokens and $1.00 per million output tokens (blended $1.00/M), with a 128,000-token context window.
Profile inherited from upstream Llama 3.1 70B ↗ — this is a hosted variant of the same open-weights model.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Anyscale's published pricing; no check date on record.
- Open weights
- 128K context
- Wide hosted availability
- Self-hosted chat
- Fine-tune base
- Cost benchmarking
Benchmarks
More from Anyscale
See all 4 →Frequently asked questions
How much does Llama 3.1 70B (Anyscale) cost?
Llama 3.1 70B (Anyscale) costs $1.00 per million input tokens and $1.00 per million output tokens, for a blended reference rate of $1.00 per million tokens.
What is Llama 3.1 70B (Anyscale)'s context window?
Llama 3.1 70B (Anyscale) supports up to 128,000 tokens of context in a single request.
What is Llama 3.1 70B (Anyscale) best for?
Llama 3.1 70B (Anyscale) is well suited to Open weights, 128K context and Wide hosted availability.
Who makes Llama 3.1 70B (Anyscale)?
Llama 3.1 70B (Anyscale) is developed and served by Anyscale. It was released in Jul 2024.
