MoonshotAI: Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Everything else
| Max output | 100K |
|---|---|
| Input / 1M | $0.6 |
| Output / 1M | $2.50 |
| Cache read / 1M | $0.15 |
| Cache write / 1M | — |
| 1M in + 1M out | $3.10 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | always on |
| Open weights | yes |
| Released | 2025-11-06 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | moonshotai/kimi-k2-thinking |
Benchmarks
| source | epoch |
|---|---|
| eci | 146.04 |
| confidence | Likely |
| accessibility | Open weights (restricted use) |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.