Kimi K2 Thinking pricing
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Kimi K2 Thinking from Moonshot AI (Kimi) costs $0.600 per 1M input tokens and $2.50 per 1M output tokens. Cached input is $0.150 per 1M. Context window 262,144 tokens.
API id kimi-k2-thinking · Moonshot AI (Kimi) · source · updated 2026-09-25 · general-purpose
$0.600
Input / 1M tokens
$2.50
Output / 1M tokens
$0.150
Cached input / 1M
262K
Context window
Kimi K2 Thinking specifications
- Provider
- Moonshot AI (Kimi)
- API id
kimi-k2-thinking- Model type
- general-purpose
- Context window
- 262K tokens
- Max output
- 98K tokens
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-09-25
Tags
- reasoning
Kimi K2 Thinking across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.600 | $0.150 | $2.50 | $3.10 | — | |
OpenRouterHost | $0.600 | $0.150 | $2.50 | $3.10 | — |
What Kimi K2 Thinking costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0019 |
| Document summary | 50,000 | 2,000 | $0.03 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $1.10 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Kimi K2 Thinking price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-09-10 | $0.600 | $2.50 |
| 2026-09-08 | $0.600 | $2.50 |
| 2026-08-11 | $0.600 | $2.50 |
Common questions
- How much does Kimi K2 Thinking cost per 1M tokens?
- Kimi K2 Thinking costs $0.600 per 1M input tokens and $2.50 per 1M output tokens on the standard tier. Cached input is $0.150 per 1M.
- What is Kimi K2 Thinking's context window?
- Kimi K2 Thinking accepts up to 262,144 tokens in a single request, and can return up to 98,304 output tokens.
- Is there a cheaper Kimi model than Kimi K2 Thinking?
- Yes. Kimi K2 0711 is $0.570 per 1M input tokens versus $0.600 for Kimi K2 Thinking, with a 131,072 token context window.
- Where does this Kimi K2 Thinking price come from?
- From the OpenRouter catalogue, because Moonshot AI (Kimi) does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from Moonshot AI (Kimi)'s own — verify before committing spend.