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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| $0.600 | $2.50 | 262K | 98.6% | |
| AtlasCloudint4 | $0.600 | $2.50 | 262K | — |
| Novitabf16 | $0.600 | $2.50 | 262K | — |
Kimi K2 Thinking costs $0.600 per million input tokens and $2.50 per million output tokens via OpenRouter, making it 173rd cheapest of 298 paid models.
Kimi K2 Thinking scores 24.1 on the Artificial Analysis Intelligence Index, ranking 104th of 178 benchmarked models, with a GPQA Diamond score of 71%.
Kimi K2 Thinking generates around 57 tokens per second with 558ms time-to-first-token (p50), the 144th fastest tracked model.
Kimi K2 Thinking supports a 262K-token context window and can output up to 262K tokens. It accepts text input.