Service Unavailable

Gemini API
,
1

Command:

echo "build a pretty pet shop website" | gemini --model gemini-3-pro-preview --output-format stream-json --approval-mode yolo

Output:

File /home/mars/.cache/vscode-ripgrep/ripgrep-v13.0.0-10-x86_64-unknown-linux-musl.tar.gz has been cached
{"type":"init","timestamp":"2025-11-24T07:45:24.019Z","session_id":"536e50f1-0b68-4b38-be7a-21a70b690868","model":"gemini-3-pro-preview"}
{"type":"message","timestamp":"2025-11-24T07:45:24.021Z","role":"user","content":"build a pretty pet shop website\n\n\n"}
Attempt 1 failed with status 503. Retrying with backoff... ApiError: {"error":{"message":"{\n  \"error\": {\n    \"code\": 503,\n    \"message\": \"The model is overloaded. Please try again later.\",\n    \"status\": \"UNAVAILABLE\"\n  }\n}\n","code":503,"status":"Service Unavailable"}}
    at throwErrorIfNotOK (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:14072:30)
    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:13863:13
    at async Models.generateContentStream (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:15204:24)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/loggingContentGenerator.js:116:26
    at async runInDevTraceSpan (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/telemetry/trace.js:33:16)
    at async retryWithBackoff (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/utils/retry.js:75:28)
    at async GeminiChat.makeApiCallAndProcessStream (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/geminiChat.js:297:32)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/geminiChat.js:232:40
    at async Turn.run (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/turn.js:65:30) {
  status: 503
}
Attempt 2 failed with status 503. Retrying with backoff... ApiError: {"error":{"message":"{\n  \"error\": {\n    \"code\": 503,\n    \"message\": \"The model is overloaded. Please try again later.\",\n    \"status\": \"UNAVAILABLE\"\n  }\n}\n","code":503,"status":"Service Unavailable"}}
    at throwErrorIfNotOK (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:14072:30)
    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:13863:13
    at async Models.generateContentStream (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs:15204:24)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/loggingContentGenerator.js:116:26
    at async runInDevTraceSpan (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/telemetry/trace.js:33:16)
    at async retryWithBackoff (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/utils/retry.js:75:28)
    at async GeminiChat.makeApiCallAndProcessStream (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/geminiChat.js:297:32)
    at async file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/geminiChat.js:232:40
    at async Turn.run (file:///home/mars/.nvm/versions/node/v22.20.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/turn.js:65:30) {
  status: 503
}
Error when talking to Gemini API Full report available at: /tmp/gemini-client-error-Turn.run-sendMessageStream-2025-11-24T07-51-30-223Z.json
{"type":"result","timestamp":"2025-11-24T07:51:30.230Z","status":"error","error":{"type":"Error","message":"[API Error: {\"error\":{\"message\":\"{\\n  \\\"error\\\": {\\n    \\\"code\\\": 503,\\n    \\\"message\\\": \\\"The model is overloaded. Please try again later.\\\",\\n    \\\"status\\\": \\\"UNAVAILABLE\\\"\\n  }\\n}\\n\",\"code\":503,\"status\":\"Service Unavailable\"}}]"},"stats":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"duration_ms":0,"tool_calls":0}}

image
image1036×714 22.2 KB

3

I got the same error as well when using nanobanana-pro APIs. A lot of server errors

5

Is Google died? No official response even for a paid user?

7

Hi @mars
503 errors are typically temporary. Recommended step is to briefly switch to a different model. If the error continues over time, please provide your region and tier so we can escalate the issue.
Thanks

9

Hi @Pannaga_J , thanks for the response. Please notice this is not a temporary issue, I’ve been getting this for all afternoon every day since the launch of Nano Banana Pro.
I’m not sure what region is, I’m calling the API from Singapore.
Project ID: gen-lang-client-0117489081
Quota tier: Tier 1

10

An error occurred during the API request: 503 Server Error: Service Unavailable for url: https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-preview:generateContent

Currently access from Malaysia.