API pricing per million tokens
- Input
- $0.57
- per 1M, DigitalOcean
- Output
- $2.4
- per 1M tokens
- Cached input
- $0.114
- no batch tier listed
- Context
- 262K
- 236K max output
Where to buy it (21)
DigitalOceandefault region$0.57 / $2.4cached $0.114
- Decartfp4, fp4$0.587 / $2.47cached $0.099
- StreamLakefp8, fp8$0.599 / $2.52cached $0.101
Chutesint4, int4$0.5 / $2.85cached $0.05
- Inceptronint4, int4$0.497 / $2.97cached $0.128
CoreWeavefp4, fp4$0.65 / $3.41cached $0.15
Crusoebf16, bf16$0.7 / $3.5cached $0.35
SiliconFlowfp8, fp8$0.77 / $3.4cached $0.14
DeepInfrafp4, fp4$0.75 / $3.5cached $0.15
Parasailint4, int4$0.75 / $3.5cached $0.16
Veniceint4, int4$0.75 / $3.5cached $0.16
Novita AIdefault region$0.8 / $3.4cached $0.16
- GMICloudfp8, fp8$0.855 / $3.6cached $0.144
- AtlasCloudint4, int4$0.95 / $4cached $0.16
- Baidufp4, fp4$0.95 / $4cached $0.16
Basetenfp4, fp4$0.95 / $4cached $0.16
Cloudflare Workers AIdefault region$0.95 / $4cached $0.16
Fireworks AIdefault region$0.95 / $4cached $0.16
Moonshot AIint4, int4$0.95 / $4cached $0.16
- Sail Researchint4, int4$1 / $4cached $0.2
- Phaladefault region$1.09 / $4.6cached $0.37
Through a gateway
Your own numbers100M input and 20M output tokens a month: $105.00 direct.
Helicone$105.00+0%
Kong AI Gateway$105.00+0%
LiteLLM$105.00+0%
Vercel AI Gateway$105.00+0%
AWS Bedrock$105.00+0%
Azure AI Foundry$105.00+0%
Google Vertex AI$105.00+0%
Databricks Mosaic AI$105.00+0%
Hugging Face Inference$105.00+0%
Requesty$110.25+5%
Eden AI$110.78+5.5%
OpenRouter$110.78+5.5%
Snowflake Cortex AI$126.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
Muse Spark 1.3Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MSep 2, 2026
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
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. Blended price $1.03 per 1M tokens at 3 input to 1 output.
Questions
How much does Kimi K2.6 cost?
$0.57 per million input tokens and $2.4 per million output tokens, with cached input at $0.114.
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 21 routes tracked, DigitalOcean is cheapest at $0.57 input and $2.4 output per million tokens.
Has Kimi K2.6's price changed?
Yes. The output price went from $1.82 to $4, first seen Sep 24, 2026.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.