Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
Llama 4 Maverick is an open-weight model from Meta, ranking #154 of 235 on the TryAii Score. Its best showing is #6 on LiveBench. It's served by 5 independent hosts from $0.2/$0.696 per million input/output tokens — about half of what models at its level usually charge.
Prompt $/1M
$0.200
Completion $/1M
$0.696
Context
1,048,576 tok
Best provider
85 tok/s · Artificial Analysis
Specs
- Model id
- meta-llama/llama-4-maverick
- Display name
- Meta: Llama 4 Maverick
- Modality
- text+image->text
- Tokenizer
- Llama4
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 115,200
- Prompt $/1M
- $0.200
- Completion $/1M
- $0.696
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Artificial Analysis | 85 |
| Googlefastest | 54 |
| Parasail | 29 |
| DeepInfra | 26 |
| Novita | 24 |
| SambaNova | 21 |
| DigitalOcean | 10 |
| meta-llamafastest | — |