Lyria 3 Clip Preview vs Llama Prompt Guard 2 22M
Side by side: price, limits, capabilities and real cost examples. Catalog data · checked Nov 16, 2026
Short answer
- Lyria 3 Clip Preview reads 2048× more text per request (1.05M vs 512 tokens).
- Only Lyria 3 Clip Preview offers: image input, audio output.
- A quality verdict needs a hands-on test. Neither model has completed our Hero suite yet, so this page compares facts, not output quality.
| Lyria 3 Clip PreviewGoogle | Llama Prompt Guard 2 22MGroq (host) | |
|---|---|---|
| Input price / 1M tokens | $0 | $0.03 |
| Output price / 1M tokens | $0 | $0.03 |
| Context window | 1.05M | 512 |
| Max output per answer | 65.5K | 512 |
| Released | Mar 2026 | Apr 2025 |
| Image input | Yes | No |
| Audio output | Yes | No |
| What it costs in practice | ||
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $0 | $0.032 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0 | $0.005 |
| 10,000 product descriptions300 input and 200 output tokens per text | $0 | $0.15 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $0 | $0.095 |
Green marks the better value in that row. Prices are first-party list prices in USD. Method.
