Meta
Llama Guard 4 12B
Released 2025-04-30 · Knowledge up to 2024-08-31
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
You send / 1M
$0.180
tokens in
It replies / 1M
$0.180
tokens out
Memory
164K
tokens it can read at once
Typical request
$0.0003
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · bf16 | $0.144 | $0.144 | n/a | Read |
| DeepInfra · bf16 | $0.180 | $0.180 | 99% | Read |
| DeepInfra · bf16 | $0.270 | $0.270 | 99% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: image, text
- Writes: text
- Reasoning: No
- Tool calling: No
- Longest reply: 16K tokens
Similar models
- Ministral 3 14B 2512Mistral · $0.200 in / $0.200 out per 1M
- UI-TARS 7B Bytedance · $0.100 in / $0.200 out per 1M
- Mistral Small 3.2 24BMistral · $0.075 in / $0.200 out per 1M
- Ministral 3 8B 2512Mistral · $0.150 in / $0.150 out per 1M
- Gemma 3 12BGoogle · $0.050 in / $0.150 out per 1M
- Nova Lite 1.0Amazon · $0.060 in / $0.240 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Vision AI ModelsTop No-Training Vision AI ModelsTop Zero Data Retention AI Models