Meta: Llama Guard 4 12B
meta-llama/llama-guard-4-12b
Llama Guard 4 12B is a Meta model that isn't ranked on the TryAii Score yet — no benchmark results on file. It lists at $0.18/$0.18 per million input/output tokens with a 163K-token context. It's on the slow side at roughly 10-13 tokens/sec.
Prompt $/1M
$0.180
Completion $/1M
$0.180
Context
163,840 tok
Best provider
14 tok/s · Together
Specs
- Model id
- meta-llama/llama-guard-4-12b
- Display name
- Meta: Llama Guard 4 12B
- Modality
- text+image->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 163,840
- Max completion
- 16,384
- Prompt $/1M
- $0.180
- Completion $/1M
- $0.180
- 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 |
|---|---|
| Togetherfastest | 14 |
| DeepInfrafastest | 9 |
| meta-llamafastest | — |