Ways to buy 20
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| Baidu fp4 · cached $0.076 | $0.452 | $1.9 | $0.452 / $1.9Cheapest | $0.076 | Cheapest |
 DigitalOceanDefault region · cached $0.114 | $0.57 | $2.4 | $0.57 / $2.4+26% vs cheapest | $0.114 | +26% vs cheapest |
| Decart fp4 · cached $0.099 | $0.587 | $2.47 | $0.587 / $2.47+30% vs cheapest | $0.099 | +30% vs cheapest |
| StreamLake fp8 · cached $0.101 | $0.599 | $2.52 | $0.599 / $2.52+32% vs cheapest | $0.101 | +32% vs cheapest |
| Inceptron int4 · cached $0.126 | $0.452 | $2.97 | $0.452 / $2.97+33% vs cheapest | $0.126 | +33% vs cheapest |
 Chutesint4 · cached $0.05 | $0.5 | $2.85 | $0.5 / $2.85+33% vs cheapest | $0.05 | +33% vs cheapest |
 CoreWeavefp4 · cached $0.15 | $0.65 | $3.41 | $0.65 / $3.41+64% vs cheapest | $0.15 | +64% vs cheapest |
 Crusoebf16 · cached $0.35 | $0.7 | $3.5 | $0.7 / $3.5+72% vs cheapest | $0.35 | +72% vs cheapest |
 SiliconFlowfp8 · cached $0.14 | $0.77 | $3.4 | $0.77 / $3.4+75% vs cheapest | $0.14 | +75% vs cheapest |
 DeepInfrafp4 · cached $0.15 | $0.75 | $3.5 | $0.75 / $3.5+76% vs cheapest | $0.15 | +76% vs cheapest |
 Parasailint4 · cached $0.16 | $0.75 | $3.5 | $0.75 / $3.5+76% vs cheapest | $0.16 | +76% vs cheapest |
 Veniceint4 · cached $0.16 | $0.75 | $3.5 | $0.75 / $3.5+76% vs cheapest | $0.16 | +76% vs cheapest |
 Novita AIDefault region · cached $0.16 | $0.8 | $3.4 | $0.8 / $3.4+78% vs cheapest | $0.16 | +78% vs cheapest |
| GMICloud fp8 · cached $0.144 | $0.855 | $3.6 | $0.855 / $3.6+89% vs cheapest | $0.144 | +89% vs cheapest |
| AtlasCloud int4 · cached $0.16 | $0.95 | $4 | $0.95 / $4+110% vs cheapest | $0.16 | +110% vs cheapest |
 Basetenfp4 · cached $0.16 | $0.95 | $4 | $0.95 / $4+110% vs cheapest | $0.16 | +110% vs cheapest |
 Cloudflare Workers AIDefault region · cached $0.16 | $0.95 | $4 | $0.95 / $4+110% vs cheapest | $0.16 | +110% vs cheapest |
 Fireworks AIDefault region · cached $0.16 | $0.95 | $4 | $0.95 / $4+110% vs cheapest | $0.16 | +110% vs cheapest |
 Moonshot AIint4 · cached $0.16 | $0.95 | $4 | $0.95 / $4+110% vs cheapest | $0.16 | +110% vs cheapest |
| Phala Default region · cached $0.37 | $1.09 | $4.6 | $1.09 / $4.6+141% vs cheapest | $0.37 | +141% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $83.30 direct.
Helicone$83.30+0%
Kong AI Gateway$83.30+0%
LiteLLM$83.30+0%
Vercel AI Gateway$83.30+0%
Requesty$87.47+5%
Eden AI$87.88+5.5%
OpenRouter$87.88+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Kimi K3 Moonshot 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 K2.5 Moonshot AI · 262K | $0.45 | $2.25 | $0.45 / $2.25 | $0.9 | 262K | on SiliconFlow (int4) | · |
| Kimi K2 Thinking Moonshot AI · 262K | $0.6 | $2.5 | $0.6 / $2.5 | $1.08 | 262K | on Google Vertex AI | · |
 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) | · |
 GLM 5.3Z.ai · 1.31M | $0.561 | $1.76 | $0.561 / $1.76 | $0.862 | 1.31M | on Baidu (fp8) | · |
| Gemini 3.7 Flash Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75100% | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | 100% |
| GLM 4.6 Z.ai · 205K | $0.43 | $1.75 | $0.43 / $1.75 | $0.76 | 205K | on Venice (fp4) | · |
About Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
Takes text, image in and returns text. First listed Sep 23, 2026. Up to 236K output tokens. Blended price $0.815 per 1M tokens at 3 input to 1 output. Model id kimi-k2-6.
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 K2.6 cost?
$0.452 per million input tokens and $1.9 per million output tokens, with cached input at $0.076.
What is the context window of Kimi K2.6?
262K tokens, with up to 236K tokens of output.
Where is Kimi K2.6 cheapest?
Of 20 routes tracked, Baidu is cheapest at $0.452 input and $1.9 output per million tokens.
Has Kimi K2.6's price changed?
Yes. The input price went from $0.497 to $0.452, first seen Sep 25, 2026.
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.