HTTP 503 Service Unavailable – MODEL_CAPACITY_EXHAUSTED for claude-opus-4-6-thinking via cloudcode-pa.googleapis.com

Gemini API
1

I’m encountering a persistent HTTP 503 Service Unavailable error when making requests to the AI service.

Error Details:



Trajectory ID: 94d0de66-57e7-4615-8c94-dd951
TraceID: 0xa4622ce2f01
Date: Tue, 12 May 2026 12:41:27 GMT
HTTP Status: 503 UNAVAILABLE
Server: ESF
Content-Type: text/event-stream

Response Body:



{
  "error": {
    "code": 503,
    "details": [
      {
        "@type": "type.googleapis.com/google.rpc.ErrorInfo",
        "domain": "cloudcode-pa.googleapis.com",
        "metadata": {
          "model": "claude-opus-4-6-thinking"
        },
        "reason": "MODEL_CAPACITY_EXHAUSTED"
      }
    ],
    "message": "No capacity available for model claude-opus-4-6-thinking on the server",
    "status": "UNAVAILABLE"
  }
}

Issue Description:

The request fails because the backend reports MODEL_CAPACITY_EXHAUSTED, indicating no available capacity for the specified model.