API pricing per million tokens
kimi-k2-thinking Open weightsChecked 5h ago
- Input
- $0.6
- per 1M, Google Vertex AI
- Output
- $2.5
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 262K
- 98K max output
Where to buy it (2)
Google Vertex AIdefault region$0.6 / $2.5$1.08 blended
Novita AIbf16, bf16$0.6 / $2.5cached $0.15
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%
AWS Bedrock$110.00+0%
Azure AI Foundry$110.00+0%
Google Vertex AI$110.00+0%
Databricks Mosaic AI$110.00+0%
Hugging Face Inference$110.00+0%
Cloudflare AI Gateway$115.50+5%
Requesty$115.50+5%
Eden AI$116.05+5.5%
OpenRouter$116.05+5.5%
Snowflake Cortex AI$132.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
BigQuery MLn/a
Cloudflare Workers AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Kimi K3Moonshot AI · via InferenceNet (fp4) · 1M$1.4 / $10.8in / out per 1M$1.4$10.8$0.31MJul 16, 2026
Kimi K2.7 CodeMoonshot AI · via StreamLake · 262K$0.713 / $3in / out per 1M$0.713$3$0.143262KJun 12, 2026
Kimi K2.6Moonshot AI · via DigitalOcean · 262K$0.57 / $2.4in / out per 1M$0.57$2.4$0.114262KApr 20, 2026
Kimi K2.5Moonshot AI · via SiliconFlow (int4) · 262K$0.45 / $2.25in / out per 1M$0.45$2.25$0.07262KJan 27, 2026
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
Muse Spark 1.1Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MJul 16, 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 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. Blended price $1.08 per 1M tokens at 3 input to 1 output.
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.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.