Inkling 2 Mini vs Inkling 2 Small
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Multimodal reasoning and coding | — |
| Published capabilities | Reuses its middle layers three times per token. Thinking Machines reports 48.2% on DeepSWE v1.1. | Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work |
| Model size | 26.4B total / 3.4B active parameters | — |
| Access | Downloadable weights and Tinker inference and customization | — |
| Operating limits | Native mixed-precision checkpoint occupies approximately 20 GB. | — |
| Sources | Model weights · Additional documentation | — |
| Inputs | Text, Images | Text, Images |
| Context window | — | 1,048,576 tokens |
| Input price per million tokens | — | $0.30 |
| Output price per million tokens | — | $1.00 |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 20, 2026 | Nov 5, 2026 |