Meta: Llama 4 Scout
meta-llama/llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Prompt $/1M
$0.100
Completion $/1M
$0.300
Context
10,000,000 tok
Best provider
98 tok/s · Artificial Analysis
Specs
- Model id
- meta-llama/llama-4-scout
- Display name
- Meta: Llama 4 Scout
- Modality
- text+image->text
- Tokenizer
- Llama4
- Instruct type
- —
- Context length
- 10,000,000
- Max completion
- 16,384
- Prompt $/1M
- $0.100
- Completion $/1M
- $0.300
- 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 | 98 |
| Groqfastest | 33 |
| 33 | |
| DeepInfra | 32 |
| Novita | 29 |