Llama 3.2 1B Instruct
Smallest Llama, 1B parameters for ultra-edge inference. Tradeoff: very limited reasoning.
Llama 3.2 1B Instruct is a efficient AI model from Meta. It costs $0.027 per million input tokens and $0.201 per million output tokens (blended $0.079/M), with a 60,000-token context window.
Profile inherited from upstream Llama 3.2 1B ↗ — this is a hosted variant of the same open-weights model.
- Smallest Llama
- Edge / mobile
- Open weights
- On-device routing
- Tiny-footprint chat
Benchmarks
More from Meta
See all 20 →Frequently asked questions
How much does Llama 3.2 1B Instruct cost?
Llama 3.2 1B Instruct costs $0.027 per million input tokens and $0.201 per million output tokens, for a blended reference rate of $0.079 per million tokens.
What is Llama 3.2 1B Instruct's context window?
Llama 3.2 1B Instruct supports up to 60,000 tokens of context in a single request.
What is Llama 3.2 1B Instruct best for?
Llama 3.2 1B Instruct is well suited to Smallest Llama, Edge / mobile and Open weights.
Who makes Llama 3.2 1B Instruct?
Llama 3.2 1B Instruct is developed and served by Meta. It was released in Sep 2024.