Meta: Llama 4 Scout
meta-llama/llama-4-scout
Llama 4 Scout (Meta) is a low-cost open-weight model priced near the bottom of the board, at $0.1/$0.3 per million input/output tokens, served by 3 independent hosts. For the money it delivers #184 of 235 on the TryAii Score. Its best showing is #9 on GSM8K. It's reasonably quick at roughly 26-98 tokens/sec.
Prompt $/1M
$0.100
Completion $/1M
$0.300
Context
1,310,720 tok
Best provider
172 tok/s · Groq
Specs
- Model id
- meta-llama/llama-4-scout
- Display name
- Meta: Llama 4 Scout
- Modality
- text+image->text
- Tokenizer
- Llama4
- Instruct type
- —
- Context length
- 1,310,720
- 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 |
|---|---|
| Groqfastest | 172 |
| Artificial Analysis | 98 |
| Googlefastest | 41 |
| Novita | 26 |
| DeepInfra | 22 |
| meta-llamafastest | — |