Kimi K2 Thinking

Model details

← Back

Kimi K2 Thinking

Model
accounts/fireworks/models/kimi-k2-thinking
Provider
fireworks
API
anthropic-messages
Base URL
https://api.fireworks.ai/inference
Input
text
Reasoning
Yes
Context window
256,000
Max tokens
256,000
Cost / million input
$0.6
Cost / million output
$2.5
Cost / million cache read
$0.3
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "fireworks": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "accounts/fireworks/models/kimi-k2-thinking",
          "name": "Kimi K2 Thinking",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 256000,
          "maxTokens": 256000,
          "cost": {
            "input": 0.6,
            "output": 2.5,
            "cacheRead": 0.3,
            "cacheWrite": 0
          }
        }
      ],
      "api": "anthropic-messages",
      "baseUrl": "https://api.fireworks.ai/inference"
    }
  }
}