SWE-2 Flash vs Ripple-65B Preview
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Software engineering | Language generation and coding |
| Published capabilities | Coding agent model developed from Inkling-Small, with mid-training on scientific and software engineering data. | Dense transformer trained on 12 trillion tokens with a focus on long-context software engineering. |
| Model size | — | 65B parameters |
| Access | Devin Desktop and CLI | Public weights and hosted inference via Together AI, OpenRouter and Fireworks |
| Sources | Publisher documentation | Publisher documentation · Model weights |
| Inputs | Text | Text |
| Context window | — | 1,048,576 tokens |
| Input price per million tokens | — | — |
| Output price per million tokens | — | — |
| Weights | Proprietary | Open weights |
| Released | Nov 4, 2026 | Nov 4, 2026 |