Compare
2–4 model comparison. Best-in-row is highlighted.
Lyria 3 Clip Preview
Google · google__lyria-3-clip-preview
Qwen3 VL 30B A3B Instructopen
Qwen · qwen__qwen3-vl-30b-a3b-instruct
Identity
| Field | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
|---|---|---|
| Provider | Qwen | |
| Slug | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | Qwen/Qwen3-VL-30B-A3B-Instruct |
Quality
| Field | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
|---|---|---|
| Input $ / 1M tokens | $0.00 | $0.15 |
| Cached input $ / 1M | — | — |
| Output $ / 1M tokens | $0.00 | $0.60 |
Context
| Field | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
|---|---|---|
| Max context tokens | 1,048,576 | 262,144 |
| Max output tokens | 65,536 | 16,384 |
Modalities
| Field | google__lyria-3-clip-preview | qwen__qwen3-vl-30b-a3b-instruct |
|---|---|---|
| Input | text, image | text, image |
| Output | text, audio | text |