Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰Google: Lyria 3 Pro Preview is 100% cheaper than Amazon Nova Lite
⚡Amazon Nova Lite is 85ms faster than Google: Lyria 3 Pro Preview
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Google: Lyria 3 Pro Preview is Infinity% cheaper
| Spec | Amazon Nova Lite | Google: Lyria 3 Pro Preview |
|---|---|---|
| Provider | amazon | |
| Input price / 1M tokens | $0.06 | Free |
| Output price / 1M tokens | $0.24 | — |
| Context window | 300k tokens | 1049k tokens |
| Latency (p50) | — |
| 85ms |
| Best benchmark score | — | — |
| Open source | No | No |
Amazon Nova Lite is a very low-cost multimodal model that can process image, video, and text inputs. Fast and accurate for a wide range of tasks requiring visual and language understanding.
Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...
Want to swap in a different model or estimate monthly costs?