MoonshotAI: Kimi K2 Thinkingmoonshotai
MoonshotAI: Kimi K2 Thinking: $0.60/1M input, $2.50/1M output, 262K context, CPS grade A. 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...
API Pricing (per 1M tokens)
| Input | $0.60 |
| Output | $2.50 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.07 |
Specs & Performance
| Context Length | 262K |
| Max Output | 98K |
| Intelligence | 22 |
| Coding | 35 |
| Math | 95 |
| Speed | — |
| TTFT | — |
| CPS Grade | A |
| Input / Output Modalities | text → text |
More from moonshotai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the MoonshotAI: Kimi K2 Thinking API cost?
MoonshotAI: Kimi K2 Thinking costs $0.60/1M input tokens and $2.50/1M output tokens. Blended cost at a 3:1 ratio is about $1.07/1M tokens.
What is the context window of MoonshotAI: Kimi K2 Thinking?
MoonshotAI: Kimi K2 Thinking supports a 262K token context window with up to 98K output tokens.
Is MoonshotAI: Kimi K2 Thinking worth it?
MoonshotAI: Kimi K2 Thinking has a CPS grade of A (score 67), intelligence index 22, coding index 35. Use the compare page to benchmark against rivals.