Compare Granite 4.1 8B from ibm-granite and Lyria 3 Pro Preview from Google on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
Granite 4.1 8B and Lyria 3 Pro Preview are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Granite 4.1 8B, from ibm-granite, has a 131,072-token context window and is priced by the provider serving it on OpenRouter.
Lyria 3 Pro Preview, from Google, has a 1,048,576-token context window and is priced at $0.08/song on OpenRouter.
| Granite 4.1 8B | Lyria 3 Pro Preview | |
|---|---|---|
| Input price | Pricing varies by provider | Not applicable |
| Output price | Pricing varies by provider | Not applicable |
| Context window | 131,072 tokens | 1,048,576 tokens |
| Intelligence Index | 6.6 | Not available |
| Coding Index | 9.5 | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | Not available | 2.36 s |
| Throughput (p50) | Not available | 11.5 tok/s |
Lyria 3 Pro Preview has the longer context window at 1,048,576 tokens, compared with 131,072 tokens for Granite 4.1 8B.