Text model API

Kimi K2 Thinking API

moonshotai/kimi-k2-thinking is an advanced reasoning-focused large language model designed to deliver deeper analytical capabilities, structured problem solving, and improved logical reasoning. Developed by Moonshot AI, this model is optimized for complex tasks that require multi-step thinking, detailed explanations, and accurate interpretation of nuanced prompts. The Kimi K2 Thinking model excels in scenarios where clarity, reasoning depth, and step-by-step analysis are essential, making it ideal for research assistance, technical problem solving, coding support, and knowledge-intensive work

Model id
kimi-k2-thinking
Takes
Text (required)
Makes
Text
Endpoint
POST /api/v1/chat/completions
Made by
Moonshot AI
Mode
Synchronous

Call Kimi K2 Thinking

Base URL https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.

Model kimi-k2-thinking

POST /api/v1/chat/completions

curl https://payload.rentprompts.com/api/v1/chat/completions \
  -H "Authorization: Bearer rp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kimi-k2-thinking",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about APIs."
    }
  ],
  "max_tokens": 256
}'

Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →

What a typical call costs

Worked out from Kimi K2 Thinking's published price (0.27 J in · 0.5 J out / 1K tokens). You pay only for successful results, from your Joule balance.
  • 1,000 input + 500 output tokens0.52 Joules
  • 10,000 input + 2,000 output tokens3.7 Joules

Send requests to POST /api/v1/chat/completions. Kimi K2 Thinking answers synchronously: the result comes back in the response to the same request. Token counts come from the model's own usage report, so a real call may use more or fewer tokens than this example.

Settings

Optional parameters this model accepts (pass them in settings on /v1/run, or as top-level fields where OpenAI defines them).
NameTypeDefaultRange / options
max_tokensinteger20482 – 20480
temperaturefloat0.10 – 2
top_pfloat10 – 2
Kimi K2 Thinking API — Pricing & Code Examples | RentPrompts