$ diff embeddinggemma-2 kimi-k2-8-preview
EmbeddingGemma 2 vs Kimi K2.8 Preview
Values come from EmbeddingGemma 2 and Kimi K2.8 Preview, 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
- closed
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Kimi K2.8 Preview takes 1M against 8K — 125× more room in a single request.
- Weights
- EmbeddingGemma 2 publishes weights (Apache 2.0); Kimi K2.8 Preview is API-only. That decides self-hosting, air-gapped deployment and fine-tuning before any capability question does.
- Recency
- EmbeddingGemma 2 shipped 25 days after Kimi K2.8 Preview (2026-10-06 vs 2026-09-11).
Full spec
| Attribute | EmbeddingGemma 2 | Kimi K2.8 Preview |
|---|---|---|
| Developer | Google DeepMind | Moonshot AI |
| Released | 2026-10-06 | 2026-09-11 |
| Context window | 8K tokens | 1,000,000 |
| Pricing | not recorded | not recorded |
| License | Apache 2.0 | proprietary |
| Availability | Weights on Hugging Face and Kaggle; local inference | Kimi API platform, Kimi Code, Kimi Work |