Llama 4 Maverick
MetaMeta's larger Llama 4 model, with image input and a 1,048,576-token context.
Main uses: Long-document and multi-image analysis at open-model pricing, via providers hosting Meta's weights.
What sets it apart: Roughly double the output price of Scout ($0.6525 vs $0.30 per 1M) for a larger model in the same family.
In
$0.19
Out
$0.65
Blended
$0.30
Where to buy this model
3 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.19 | $0.65 | $0.30 | - | |
| $0.35 | $1.00 | $0.51 | +70% | |
| $0.35 | $1.15 | $0.55 | +83% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 524K
- max output
- 16K
- cache read /1M
- $0.05
- 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 | $0.1 | $0.3 | 1.31072M |
| Llama 3.3 70B Instruct | $0.1 | $0.32 | 131K |
| Llama 4 Maverick · this model | $0.188 | $0.652 | 524K |