EKA-1 vs Dhīr 5B MoE
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Multilingual reasoning and coding | Multilingual assistant |
| Published capabilities | Trained on about 7.5 trillion tokens across English and all 22 scheduled Indian languages. | Mixture-of-experts assistant supporting English and ten Indian languages for offline deployment. |
| Model size | 26.3B parameters | 5.09B total / 1.79B active |
| Access | Released through the IndiaAI Mission | Open weights for on-premises or offline use |
| Sources | Publisher documentation | Publisher documentation · Additional documentation |
| Inputs | Text | Text |
| Context window | — | 16,384 tokens |
| Input price per million tokens | — | — |
| Output price per million tokens | — | — |
| Weights | Weights unconfirmed | Open weights |
| Released | Nov 3, 2026 | Nov 3, 2026 |