Kimi K2 Thinking Turbo

Models

Model details

Kimi K2 Thinking Turbo

Model
kimi-k2-thinking-turbo
Provider
moonshotai
API
openai-completions
Base URL
https://api.moonshot.ai/v1
Input
text
Reasoning
Yes
Context window
262,144
Max tokens
262,144
Cost / million input
$1.15
Cost / million output
$8
Cost / million cache read
$0.15
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "moonshotai": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "kimi-k2-thinking-turbo",
          "name": "Kimi K2 Thinking Turbo",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 262144,
          "maxTokens": 262144,
          "cost": {
            "input": 1.15,
            "output": 8,
            "cacheRead": 0.15,
            "cacheWrite": 0
          },
          "compat": {
            "supportsStore": false,
            "supportsDeveloperRole": false,
            "supportsReasoningEffort": false,
            "maxTokensField": "max_tokens",
            "supportsStrictMode": false
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://api.moonshot.ai/v1"
    }
  }
}