Skip to main content
Moonshot AI is the company behind the Kimi series of models, featuring the Kimi K2 with 1 trillion total parameters. These models excel at agentic coding, reasoning, and general-purpose tasks. Website: https://platform.moonshot.ai/

​
Getting an API Key

  1. Sign Up/Sign In: Go to Moonshot AI Platform. Create an account or sign in.
  2. Navigate to API Keys: Access the API key management section.
  3. Create a Key: Generate a new API key.
  4. Copy the Key: Copy the API key immediately and store it securely.

​
Supported Models

Cline supports the following Moonshot models:
  • kimi-k2.5 - Latest model with 262K context, vision support, and prompt caching (0.60/0.60/3.00 per 1M tokens)
  • kimi-k2-0905-preview (Default) - September update with 262K context (0.60/0.60/2.50 per 1M tokens)
  • kimi-k2-0711-preview - July update with 131K context (0.60/0.60/2.50 per 1M tokens)
  • kimi-k2-turbo-preview - High-performance turbo variant with 262K context (2.40/2.40/10.00 per 1M tokens)
  • kimi-k2-thinking - Reasoning model with step-by-step thinking (262K context, 0.60/0.60/2.50 per 1M tokens)
  • kimi-k2-thinking-turbo - Fast reasoning variant (262K context, 2.40/2.40/10.00 per 1M tokens)

​
Configuration in Cline

  1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
  2. Select Provider: Choose “Moonshot” from the “API Provider” dropdown.
  3. Enter API Key: Paste your Moonshot API key into the “Moonshot API Key” field.
  4. Select Model: Choose your desired model from the “Model” dropdown.

​
Tips and Notes

  • Large Context: Models support up to 262K token context windows for extensive codebases.
  • Thinking Models: The kimi-k2-thinking variants provide step-by-step reasoning for complex tasks.
  • Prompt Caching: Kimi K2.5 supports prompt caching with significant cost savings on cached reads.
  • Pricing: Refer to the Moonshot pricing page for current rates.