Kimi K2.7 Code API: long-context coding model for repositories and agents

{
  "model": "kimi-k2.7-code",
  "input": {
    "model": "kimi-k2.7-code",
    "max_tokens": 2048,
    "messages": [
      {
        "role": "user",
        "content": "Review this migration plan as a senior engineer and list the risky assumptions."
      }
    ],
    "temperature": 0.7,
    "top_p": 1
  },
  "output": "A rate limit caps how many requests an API accepts from you in a given window. Once you exceed it, the server stops doing work for you and answers **429 Too Many Requests** instead.\n\n## Handling 429\n\n1. Read the `Retry-After` response header. When present it tells you exactly how long to wait, in seconds.\n2. When it is absent, back off exponentially with jitter so retries from many clients do not line up.\n3. Cap the number of retries, then surface the failure instead of looping forever.\n\n```js\nasync function withRetry(request, maxRetries = 4) {\n  for (let attempt = 0; ; attempt++) {\n    const response = await request();\n    if (response.status !== 429 || attempt === maxRetries) return response;\n    const retryAfter = Number(response.headers.get(\"retry-after\"));\n    const backoff = Number.isFinite(retryAfter) ? retryAfter * 1000 : 2 ** attempt * 500 + Math.random() * 250;\n    await new Promise((resolve) => setTimeout(resolve, backoff));\n  }\n}\n```\n\nTreat the limit as a budget you plan around, not an error you retry your way out of: batch requests where you can, cache repeated reads, and spread bulk work over time.",
  "metrics": {
    "input_tokens": 26,
    "output_tokens": 214,
    "generated_in_seconds": 4.1
  },
  "example": true
}