Kimi K2 Thinking
kimi-thinking
Thinking Kimi model for slower research passes, planning, and hard technical questions
ReasoningTool CallingOpen Weights
Context Window
262K
Max Output
262K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
2024-08
Released
2025-11-06
Last Updated
2025-11-06
Modalities
Input:Text
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| SWE-Bench Verified | 71.3 | resolved |
Available Providers (8)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 Qiniu | — | — | — | — | — | — |
 Vercel AI Gateway | Rp 8.476 | Rp 36.068 | Rp 2.543 | — | ✓ | — |
 NovitaAI | Rp 10.821 | Rp 45.085 | Rp 2.706 | — | ✓ | — |
 ZenMux | Rp 10.821 | Rp 45.085 | Rp 2.706 | — | ✓ | — |
 Merge Gateway | Rp 10.821 | Rp 45.085 | — | — | toggle, budget_tokens | — |
 Kilo Gateway | Rp 8.476 | Rp 36.068 | Rp 3.607 | — | toggle | — |
 OpenRouter | Rp 10.821 | Rp 45.085 | Rp 2.706 | — | ✓ | — |
 NanoGPT | Rp 5.411 | Rp 21.641 | — | — | — | — |