Kimi K2 Thinking API pricing
As of October 22, 2026, MoonshotAI Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens, the median of 2 providers on OpenRouter, with cached input at $0.15 per million.
Kimi K2 Thinking benchmarks and specs · Every Moonshot AI model's price
- Input, per million tokens$0.60
- Output, per million tokens$2.50
- Cached input, per million$0.15
- Context window262K tokens
- Max output98K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0019 | $1.85 | Yes |
| Repository review | 50K input + 3K output tokens | $0.037 | $37.50 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.145 | $145.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.61 | $610.00 |
Price history
The price of Kimi K2 Thinking here is the median across 2 providers on OpenRouter, so we do not track price changes for it.
Cheaper models as good as Kimi K2 Thinking
Kimi K2 Thinking has no overall or coding score, so we make no quality claim against it.
Kimi K2 Thinking pricing questions
- How much does Kimi K2 Thinking cost per million tokens?
- $0.60 per million input tokens and $2.50 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Kimi K2 Thinking support prompt caching?
- Yes. OpenRouter lists cached input at $0.15 per million tokens, against $0.60 for uncached input.
- Has the price of Kimi K2 Thinking changed?
- The price of Kimi K2 Thinking here is the median across 2 providers on OpenRouter, so we do not track price changes for it.