Llama 3.2 3B Instruct
Edge-targeted Llama 3.2, designed for on-device assistants on phones and laptops.
Llama 3.2 3B Instruct is a efficient AI model from Meta. It costs $0.050 per million input tokens and $0.330 per million output tokens (blended $0.134/M), with a 131,072-token context window.
Profile inherited from upstream Llama 3.2 3B ↗ — this is a hosted variant of the same open-weights model.
0.0%over 91 days · hover to read
- Runs on-device
- Open weights
- 128K context
- Mobile/edge assistants
- On-device summarisation
Benchmarks
More from Meta
See all 20 →Price history
12 recorded changes| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 27 Jul 2026 | Input | $0.051 | $0.050 | -1.8% |
| 27 Jul 2026 | Output | $0.335 | $0.330 | -1.5% |
| 26 Jul 2026 | Output | $0.330 | $0.335 | +1.5% |
| 26 Jul 2026 | Input | $0.050 | $0.051 | +1.8% |
| 23 Jul 2026 | Input | $0.051 | $0.050 | -1.8% |
| 23 Jul 2026 | Output | $0.335 | $0.330 | -1.5% |
| 17 Jul 2026 | Output | $0.330 | $0.335 | +1.5% |
| 17 Jul 2026 | Input | $0.050 | $0.051 | +1.8% |
| 7 Jul 2026 | Output | $0.335 | $0.330 | -1.5% |
| 7 Jul 2026 | Input | $0.051 | $0.050 | -1.8% |
| 16 May 2026 | Input | $0.051 | $0.051 | -0.2% |
| 16 May 2026 | Output | $0.340 | $0.335 | -1.5% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does Llama 3.2 3B Instruct cost?
Llama 3.2 3B Instruct costs $0.050 per million input tokens and $0.330 per million output tokens, for a blended reference rate of $0.134 per million tokens.
What is Llama 3.2 3B Instruct's context window?
Llama 3.2 3B Instruct supports up to 131,072 tokens of context in a single request.
What is Llama 3.2 3B Instruct best for?
Llama 3.2 3B Instruct is well suited to Runs on-device, Open weights and 128K context.
Who makes Llama 3.2 3B Instruct?
Llama 3.2 3B Instruct is developed and served by Meta. It was released in Sep 2024.