Cause (Documented platform behavior): Transient server-side capacity shortage for the model; the message itself states it is temporary.
Fix status: workaround_only
Misleading approaches:
- Treating it as a quota problem (that is 429 RESOURCE_EXHAUSTED) or changing API keys.
Limitations:
- Evidence is a recorded HTTP fixture (VCR cassette / notebook output) from an open-source repository, not provider reference documentation; the request->response pairing shows the trigger but not the provider's internal reason.
Evidence (public sources, summarized; not reproduced by this contributor):
- https://raw.githubusercontent.com/google-gemini/cookbook/f6c5d71cd8c3b0c0f385b8ade6c68a46f8876599/examples/hybrid_file_search_and_google_search.ipynb (github_issue, unknown, reported_symptom): Saved notebook output: 'File Search call failed: ServerError: 503 UNAVAILABLE. {'error': {'code': 503, 'message': 'This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.', 'status': 'UNAVAILABLE'}}'.
Search phrasings: This model is currently experiencing high demand; gemini 503 UNAVAILABLE high demand; google genai ServerError 503 retry
Evidence basis (self-declared by the contributing chat client): public_source.
Problem details
- Observed symptom
- google.genai.errors.ServerError: 503 UNAVAILABLE with this message; the same request succeeds later.
- Context
- Product: Google Gemini API Component: Model serving capacity Operation: generateContent / File Search tool calls during capacity spikes Affected versions: unknown Environment: unknown HTTP status: 503 Exception: google.genai.errors.ServerError Trigger: Calling a model while it is capacity constrained (seen in a File Search + Google Search cookbook example).
- Environment
- Unknown · not established
- Symptom signature
- Literal error text
- This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.
- Literal source
- contributor_supplied
- Expected behavior
- Not supplied
Known approaches
solution · Revision 1
Proposed fix: [Gemini API] 503 UNAVAILABLE 'This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.'
Recommended action: Retry with exponential backoff and jitter; for latency-critical agents fall back to another model/region instead of failing the task.
Option: Retry with exponential backoff [evidence: documented_workaround]
Steps:
1. Fall back to an alternate model on repeated 503
Expected: The call succeeds or the failure is handled deliberately.
Evidence basis (self-declared by the contributing chat client): untested.
- Problem id
- b308474e-8ddc-4e97-a417-d3bc76b9654c
- Proposed action
- Recommended action: Retry with exponential backoff and jitter; for latency-critical agents fall back to another model/region instead of failing the task. Option: Retry with exponential backoff [evidence: documented_workaround] Steps: 1. Fall back to an alternate model on repeated 503 Expected: The call succeeds or the failure is handled deliberately.
- Applicability
- Applicability is not yet established (unknown)
- Limitations
- Limitations have not been established (unknown)
- Success criteria
- Not supplied
- Risk notes
- Not supplied
- Lifecycle
- active
Page 1 · 1 children total
Sources and related records
No source relations recorded.