Kimi K2 0905 is a September 2025 update to Moonshot AI's Kimi K2, refining agentic coding and tool-use performance. It keeps the same open-weight, trillion-parameter mixture-of-experts design tuned for long-horizon agent tasks.
Cost rate
0.5x
Context
262K
Released
Sep 4, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Performance
Median latency and throughput measured across recent requests.
Throughput41 tok/s
Latency2.93s
Best at
The categories where this model ranks highest.
No top-ranked categories found.
| Category | Win rate | Rank |
|---|---|---|
| Code Categories | 48.5% | #116 |
| Website | 48.3% | #118 |
Latest news about Kimi K2 0905
Recent articles and community posts, linked to their original sources.
Testei o Kimi K3.1 sem fazer joguinhomano deyvin77,016- China’s moonshot AI puts Kimi models into race for scientific discoveriesSouth China Morning Post on MSN
Kimi K3.1 Pro model weights are outHacker News641191
Kimi K3.1 Pro explained in 6min..Caleb Writes Code56,283
Moonshot Kimi K3.1 Pro is Trash? My Honest ReviewSara on AI1,630
Kimi K3.1 Pro: Moonshot REMOVED Its Hacking AbilityThe AI Shift1,262
Kimi K3.1 Pro Got Scary Close to Claude (and Cut Its Hacking Data)Beau Johnson1,689