Kimi K2-Thinking-0905 vs Kimi K2.8 Preview
Comparing Kimi K2-Thinking-0905 and Kimi K2.8 Preview across benchmarks, pricing, and capabilities.
Moonshot AI · Moonshot AI · Updated for 2026
Which is better?
Kimi K2-Thinking-0905 and Kimi K2.8 Preview trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.
Kimi K2.8 Preview also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Kimi K2-Thinking-0905
- you need open weights you can self-host or fine-tune
Choose Kimi K2.8 Preview
- you process long inputs — it offers a 1,048,576 token context window
- you want the most recent training data — it shipped Sep 2026
At a glance
The differences that matter most.
Individual benchmarks
21 reported for Kimi K2-Thinking-0905 · 0 for Kimi K2.8 Preview
Kimi K2-Thinking-0905 and Kimi K2.8 Previewdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Human preference
Blind head-to-head votes and playground preference scores
Context Window
Maximum input and output token capacity
Kimi K2.8 Preview accepts 1,048,576 input tokens compared to Kimi K2-Thinking-0905's 262,144 tokens. Only Kimi K2-Thinking-0905 specifies output context (262,144 tokens).
Input capabilities
Documented input modalities across available providers
Kimi K2.8 Preview supports multimodal inputs, whereas Kimi K2-Thinking-0905 does not.
Kimi K2.8 Preview can handle both text and other forms of data like images, making it suitable for multimodal applications.
Kimi K2-Thinking-0905
Kimi K2.8 Preview
License
Usage and distribution terms
Kimi K2-Thinking-0905 is licensed under MIT, while Kimi K2.8 Preview uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
Kimi K2-Thinking-0905 was released on 2025-09-05, while Kimi K2.8 Preview was released on 2026-09-11.
Kimi K2.8 Preview is 12 months newer than Kimi K2-Thinking-0905.
Sep 5, 2025
1.0 years ago
Sep 11, 2026
3 days ago
1.0yr newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Kimi K2-Thinking-0905 is available from DeepInfra, Novita, Fireworks. Kimi K2.8 Preview is available from Moonshot AI.
Kimi K2-Thinking-0905
Kimi K2.8 Preview
Outputs Comparison
Judge for yourself.
Run your own prompts against Kimi K2-Thinking-0905 and Kimi K2.8 Preview side-by-side, then vote on the output you prefer.
FAQ
Common questions about Kimi K2-Thinking-0905 vs Kimi K2.8 Preview.