Moonshot Kimi

curl -X POST "https://api.runpod.ai/v2/moonshot-kimi/runsync" \
  -H "Authorization: Bearer $RUNPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "model": "kimi-k3",
      "reasoning_effort": "max",
      "max_tokens": 2048,
      "messages": [
        { "role": "system", "content": "You are Kimi." },
        { "role": "user", "content": "What is Runpod?" }
      ]
    }
  }'

import os
import requests

RUNPOD_API_KEY = os.environ["RUNPOD_API_KEY"]

response = requests.post(
    "https://api.runpod.ai/v2/moonshot-kimi/runsync",
    headers={
        "Authorization": f"Bearer {RUNPOD_API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "input": {
            "model": "kimi-k3",
            "reasoning_effort": "max",
            "max_tokens": 2048,
            "messages": [
                {"role": "system", "content": "You are Kimi."},
                {"role": "user", "content": "What is Runpod?"},
            ],
        }
    },
)

result = response.json()

# output is a list; the completion sits under result
completion = result["output"][0]["result"]
print(completion["choices"][0]["message"]["content"])
print(completion["choices"][0]["message"].get("reasoning_content"))
print(completion["choices"][0]["finish_reason"])   # "length" if max_tokens was reached
print(completion["usage"])
print(result["output"][0]["cost"])

const response = await fetch(
  "https://api.runpod.ai/v2/moonshot-kimi/runsync",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.RUNPOD_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      input: {
        model: "kimi-k3",
        reasoning_effort: "max",
        max_tokens: 2048,
        messages: [
          { role: "system", content: "You are Kimi." },
          { role: "user", content: "What is Runpod?" },
        ],
      },
    }),
  }
);

const result = await response.json();

// output is an array; the completion sits under result
const completion = result.output[0].result;
console.log(completion.choices[0].message.content);
console.log(completion.choices[0].message.reasoning_content);
console.log(completion.choices[0].finish_reason); // "length" if max_tokens was reached
console.log(completion.usage);
console.log(result.output[0].cost);

{
  "id": "sync-a1b2c3d4-e5f6-7890-abcd-ef1234567890-u1",
  "status": "COMPLETED",
  "delayTime": 89,
  "executionTime": 10078,
  "workerId": "wp3m0d84tlio47",
  "output": [
    {
      "cost": 0.0030309,
      "result": {
        "id": "chatcmpl-6aaa2dce25da6d26c138da0d",
        "object": "chat.completion",
        "model": "kimi-k3",
        "created": 1789537742,
        "choices": [
          {
            "index": 0,
            "finish_reason": "length",
            "message": {
              "role": "assistant",
              "content": "...",
              "reasoning_content": "..."
            }
          }
        ],
        "usage": {
          "prompt_tokens": 103,
          "completion_tokens": 200,
          "completion_tokens_details": { "reasoning_tokens": 197 },
          "prompt_tokens_details": { "cached_tokens": 103 },
          "cached_tokens": 103,
          "total_tokens": 303
        }
      }
    }
  ]
}

{
  "id": "sync-a1b2c3d4-e5f6-7890-abcd-ef1234567890-u1",
  "status": "FAILED",
  "error": "Invalid messages format"
}