Llama Guard 4 12B
- Input / output
- $0.144 / $0.144
- Providers
- 1
- Spread
- 1.88×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 160K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| bf16 | $0.144 | $0.144 | $0.144 | ref | |||
| bf16 | $0.18 | $0.18 | $0.18 | +25% | |||
DeepInfrabf16/priority bf16 | $0.27 | $0.27 | $0.27 | +88% |
- DeepInfraCheapestbf16/flex$0.144$0.144 in · $0.144 outref vs ref160K ctx100% uptimebf16
- $0.18$0.18 in · $0.18 out+25% vs ref160K ctx99.7% uptimebf16
- bf16/priority$0.27$0.27 in · $0.27 out+88% vs ref160K ctx99.7% uptimebf16
Blended = (3 × input + output) / 4. Ref $0.144 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Changes
About
The cheapest provider for Llama Guard 4 12B is DeepInfra at $0.144 per 1M tokens (blended), charging $0.144 per 1M input and $0.144 per 1M output tokens. It is served by a single provider. Context window: 160K tokens. Prices tracked since Oct 3, 2026.
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...
- Released
- Apr 30, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- meta-llama/llama-guard-4-12b
- Weights
- meta-llama/Llama-Guard-4-12B