Sage S2.1 Flash vs SenseNova-Loop-9B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Multimodal scientific reasoning | Vision-language reasoning |
| Published capabilities | Analyzes scientific inputs including molecular graphs, crystal structures and protein sequences, using tools to verify intermediate results. | Reuses middle layers to perform 56 layer executions with 32 physical decoder layers. |
| Model size | 321B parameters | 9B parameters |
| Access | Public checkpoint with vLLM and SGLang support | Public weights including quantized variants for local inference |
| Sources | Model weights | Model weights |
| Inputs | Text, Images | Text, Images |
| Context window | — | 524,288 tokens |
| Input price per million tokens | — | — |
| Output price per million tokens | — | — |
| Weights | Open weights | Open weights |
| Released | Nov 17, 2026 | Nov 17, 2026 |