Moonshot AI models: APIs and prices

Text generation5

• Kimi K2.5kimi-k2.5

  Moonshot Kimi K2.5. 256K context, with prompt caching.

  Input 0.2426Credits/K·Output 1.011Credits/K
• Kimi K2.6kimi-k2.6

  Moonshot Kimi K2.6. 256K context.

  Input 0.2426Credits/K·Output 1.011Credits/K
• Kimi K2.7 Codekimi-k2.7-code

  Moonshot Kimi K2.7, the coding-specialised version. 256K context.

  Input 0.2426Credits/K·Output 1.011Credits/K
• Kimi K3kimi-k3

  Moonshot Kimi K3. 256K context, with prompt caching.

  Input 1.2Credits/K·Output 6Credits/K
• Kimi K3 1013kimi-k3-1013

  Moonshot Kimi K3 on a separate line. 256K context, with prompt caching.

  Input 0.9Credits/K1.2Credits·Output 4.5Credits/K6Credits

FAQ

How do I call Moonshot AI models?

Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://api.dflop.top/v1 and put the model ID from the list above in the model field. The OpenAI, Anthropic and Gemini SDKs all work.

How are Moonshot AI models billed?

Each model is billed its own way: text models per input and output token, image models per image, video models per second or per token. Prices are in credits (60 credits = ¥1); each model page lists the full price.