API pricing per million tokens
kimi-k2 Open weightsChecked 5h ago
- Input
- $0.57
- per 1M, Novita AI (fp8)
- Output
- $2.3
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 131K
- 98K max output
Where to buy it (1)
Novita AIfp8, fp8$0.57 / $2.3$1 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $103.00 direct.
Helicone$103.00+0%
Kong AI Gateway$103.00+0%
LiteLLM$103.00+0%
Vercel AI Gateway$103.00+0%
AWS Bedrock$103.00+0%
Azure AI Foundry$103.00+0%
Google Vertex AI$103.00+0%
Databricks Mosaic AI$103.00+0%
Hugging Face Inference$103.00+0%
Cloudflare AI Gateway$108.15+5%
Requesty$108.15+5%
Eden AI$108.67+5.5%
OpenRouter$108.67+5.5%
Snowflake Cortex AI$123.60+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative 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
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 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $1 per 1M tokens at 3 input to 1 output.
Questions
How much does Kimi K2 0711 cost?
$0.57 per million input tokens and $2.3 per million output tokens.
What is the context window of Kimi K2 0711?
131K tokens, with up to 98K tokens of output.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.