$ diff embeddinggemma-2 kolibri-1
EmbeddingGemma 2 vs Kolibri-1
Values come from EmbeddingGemma 2 and Kolibri-1, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
Google DeepMindEmbeddingGemma 2
- context
- 8K
- weights
- open
- $/M in
- —
- $/M out
- —
- context
- 16K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Kolibri-1 takes 16K against 8K — 2.0× more room in a single request.
- Weights
- Both publish weights — EmbeddingGemma 2 under Apache 2.0, Kolibri-1 under Apache 2.0. Check the licences rather than assuming they permit the same commercial use.
- Recency
- EmbeddingGemma 2 shipped 3 days after Kolibri-1 (2026-10-06 vs 2026-10-03).
Full spec
| Attribute | EmbeddingGemma 2 | Kolibri-1 |
|---|---|---|
| Developer | Google DeepMind | Aleph Alpha |
| Released | 2026-10-06 | 2026-10-03 |
| Context window | 8K tokens | 16,384 tokens native; up to 1,048,576 extended |
| Pricing | not recorded | not recorded |
| License | Apache 2.0 | Apache 2.0 |
| Availability | Weights on Hugging Face and Kaggle; local inference | full weights on Hugging Face |