Kimi K2 Thinking pricing and routing profile
Kimi K2 Thinking from Moonshot AI lists at $0.60 per million input tokens and $2.50 per million output tokens, with a 262,144-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured outputReasoning controlLog probabilities
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.385 |
| Chat reply (2,000 in, 400 out) | $2.20 |
| Retrieval-augmented answer (8,000 in, 500 out) | $6.05 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Yes. At least one host return token log probabilities for Kimi K2 Thinking, which is the confidence signal Gimbix uses to let a cheaper model answer first.
Cheaper models that can answer first
Models priced below Kimi K2 Thinking that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| R1 0528 | $0.50 / $2.15 | 15% |
| Kimi K2.5 | $0.45 / $2.25 | 18% |
| Qwen3.6 Plus | $0.325 / $1.95 | 35% |
| DeepSeek V4 Flash Vision Exp | $0.44 / $1.32 | 36% |
| Qwen3 235B A22B Thinking 2507 | $0.23 / $2.30 | 37% |
| Qwen3 VL 30B A3B Thinking | $0.20 / $2.40 | 38% |
Questions
How much does Kimi K2 Thinking cost?
Kimi K2 Thinking lists at $0.60 per million input tokens and $2.50 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $2.20 per 1,000 requests.
What is the context window of Kimi K2 Thinking?
262,144 tokens.
Can a cheaper model replace Kimi K2 Thinking?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Kimi K2 Thinking on one half of your requests and make at most three answers worse on the other.