$ diff kimi-k2-8-preview inkling
Kimi K2.8 Preview vs Inkling
Values come from Kimi K2.8 Preview and Inkling, 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 K2.8 Preview
- context
- 1M
- weights
- closed
- $/M in
- —
- $/M out
- —
- context
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Identical — both accept 1M tokens, so context length is not a reason to pick either.
- Weights
- Inkling publishes weights (Apache 2.0 (open-weight)); Kimi K2.8 Preview is API-only. That decides self-hosting, air-gapped deployment and fine-tuning before any capability question does.
- Recency
- Kimi K2.8 Preview shipped 58 days after Inkling (2026-09-11 vs 2026-07-15).
Full spec
| Attribute | Kimi K2.8 Preview | Inkling |
|---|---|---|
| Developer | Moonshot AI | Thinking Machines |
| Released | 2026-09-11 | 2026-07-15 |
| Context window | 1,000,000 | 1M |
| Pricing | not recorded | not recorded |
| License | proprietary | Apache 2.0 (open-weight) |
| Availability | Kimi API platform, Kimi Code, Kimi Work | Hugging Face (BF16 and NVFP4), Tinker (fine-tuning), SGLang, vLLM, llama.cpp, Unsloth |