$ diff kimi-k3-1-pro embeddinggemma-2
Kimi K3.1 Pro vs EmbeddingGemma 2
Values come from Kimi K3.1 Pro and EmbeddingGemma 2, 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.
Moonshot AIKimi K3.1 Pro
- context
- 1.0M
- weights
- —
- $/M in
- $2
- $/M out
- $10
- context
- 8K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Kimi K3.1 Pro takes 1.0M against 8K — 131.1× more room in a single request.
- Recency
- Kimi K3.1 Pro shipped 17 days after EmbeddingGemma 2 (2026-10-23 vs 2026-10-06).
Full spec
| Attribute | Kimi K3.1 Pro | EmbeddingGemma 2 |
|---|---|---|
| Developer | Moonshot AI | Google DeepMind |
| Released | 2026-10-23 | 2026-10-06 |
| Context window | 1,048,576 tokens ([source](../../sources/blogs/moonshot-2026-10-24-k3-pricing.md)) | 8K tokens |
| Pricing | $2.00/MTok input · $10.00/MTok output · $0.20/MTok cached input; cache writes $2.00/MTok (5m), $4.00/MTok (1h); excludes taxes ([source](../../sources/blogs/moonshot-2026-10-24-k3-pricing.md)) | not recorded |
| License | not recorded | Apache 2.0 |
| Availability | Kimi.ai, mobile apps, Kimi Work, Kimi Code, Kimi API; enterprise access off by default at launch ([source](../../sources/blogs/moonshot-2026-10-23-kimi-k3-1-pro.md)) | Weights on Hugging Face and Kaggle; local inference |