Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
 Google Vertex AIDefault region | $0.6 | $2.5 | $0.6 / $2.5Cheapest | n/a | Cheapest |
 Novita AIbf16 · cached $0.15 | $0.6 | $2.5 | $0.6 / $2.5Cheapest | $0.15 | Cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $110.00 direct.
Helicone$110.00+0%
Kong AI Gateway$110.00+0%
LiteLLM$110.00+0%
Vercel AI Gateway$110.00+0%
Cloudflare AI Gateway$115.50+5%
Requesty$115.50+5%
Eden AI$116.05+5.5%
OpenRouter$116.05+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
 Kimi K3Moonshot AI · 1M | $0.885 | $10.5 | $0.885 / $10.5 | $3.3 | 1M | on Sail Research (fp4) | · |
| Kimi K2.7 Code Moonshot AI · 262K | $0.713 | $3 | $0.713 / $3 | $1.28 | 262K | on StreamLake | · |
| Kimi K2.6 Moonshot AI · 262K | $0.452 | $1.9 | $0.452 / $1.9 | $0.815 | 262K | on Baidu (fp4) | · |
| Kimi K2.5 Moonshot AI · 262K | $0.45 | $2.25 | $0.45 / $2.25 | $0.9 | 262K | on SiliconFlow (int4) | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Gemini 3.8 FlashGoogle · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · |
| Muse Spark 1.1 Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 GLM 5.3Z.ai · 1.31M | $0.561 | $1.76 | $0.561 / $1.76 | $0.862 | 1.31M | on Baidu (fp8) | · |
About 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.
Takes text in and returns text. First listed Sep 23, 2026. Up to 98K output tokens. Blended price $1.08 per 1M tokens at 3 input to 1 output. Model id kimi-k2-thinking.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across fru.devCompany profileGrowth, $3.5B (2026-07)
Questions
How much does Kimi K2 Thinking cost?
$0.6 per million input tokens and $2.5 per million output tokens.
What is the context window of Kimi K2 Thinking?
262K tokens, with up to 98K tokens of output.
Where is Kimi K2 Thinking cheapest?
Of 2 routes tracked, Google Vertex AI is cheapest at $0.6 input and $2.5 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.