$ diff embeddinggemma-2 laguna-s-2-1
EmbeddingGemma 2 vs Laguna S 2.1
Values come from EmbeddingGemma 2 and Laguna S 2.1, 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
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Laguna S 2.1 takes 1M against 8K — 125× more room in a single request.
- Weights
- Both publish weights — EmbeddingGemma 2 under Apache 2.0, Laguna S 2.1 under OpenMDW-1.1 (open-weight). Check the licences rather than assuming they permit the same commercial use.
- Recency
- EmbeddingGemma 2 shipped 77 days after Laguna S 2.1 (2026-10-06 vs 2026-07-21).
Full spec
| Attribute | EmbeddingGemma 2 | Laguna S 2.1 |
|---|---|---|
| Developer | Google DeepMind | Poolside |
| Released | 2026-10-06 | 2026-07-21 |
| Context window | 8K tokens | 1M |
| Pricing | not recorded | not recorded |
| License | Apache 2.0 | OpenMDW-1.1 (open-weight) |
| Availability | Weights on Hugging Face and Kaggle; local inference | Hugging Face |