Llama 4 Scout
MetaMeta's smaller, cheaper Llama 4 model, with the largest context window in this selection.
Main uses: Processing very long documents or codebases where a 1,310,720-token context matters more than raw model size.
What sets it apart: At $0.10/$0.30 per 1M tokens, the cheapest image-capable model with image input in this selection.
In
$0.10
Out
$0.30
Blended
$0.15
Where to buy this model
2 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.08 | $0.24 | $0.12 | - | |
| $0.25 | $0.70 | $0.36 | +200% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 1.31072M
- max output
- 16K
- Family
- llama
- Modalities
- text · image
- Features
- json · tools
Live pricing, updated 2026-11-03.
Meta models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Llama 4 Scout · this model | $0.1 | $0.3 | 1.31072M |
| Llama 3.3 70B Instruct | $0.1 | $0.32 | 131K |
| Llama 4 Maverick | $0.188 | $0.652 | 524K |