Safety classifier-style Llama Guard on Groq for moderating user or model text. Pair with a chat model rather than using Guard alone for generation.
Privacy first counting
TokenCALC counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.
Pricing snapshot
USD per 1 million tokens. Verify against the provider source before you lock budget.
| Rate | USD |
|---|---|
| Input / 1M | $0.200 |
| Output / 1M | $0.200 |
Model details
| Detail | Value |
|---|---|
| Provider | Groq |
| Context window | 8.2K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | llama-guard-3-8b |