Llama 4 Maverick
MetaLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
In
$0.19
Out
$0.65
Blended
$0.30
Where to buy this model
5 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.19 | $0.65 | $0.30 | - | |
| $0.20 | $0.80 | $0.35 | +17% | |
| $0.27 | $0.85 | $0.42 | +40% | |
| $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
- 1.048576M
- max output
- 16K
- Family
- llama
- Modalities
- text · image
- Features
- json · tools
Live pricing, updated 2026-09-15.