Google Cloud Vertex AI (Gemini Enterprise Agent Platform) · model
gemini-1.5-pro-002 deprecation: shutdown date & replacement
- Provider
- Google Cloud Vertex AI (Gemini Enterprise Agent Platform)
- Type
- model
- Announced
- —
- Shutdown
- Replacement
gemini-2.5-flash- Source
- Official Google Cloud Vertex AI (Gemini Enterprise Agent Platform) notice
Vertex AI / Gemini Enterprise Agent Platform retirement date (page says timelines may be extended but not moved earlier).
How to migrate off gemini-1.5-pro-002
- Find every place that references it:
grep -rn --exclude-dir={node_modules,.git,dist} "gemini-1.5-pro-002" . - Replace the model ID:
- model: "gemini-1.5-pro-002" + model: "gemini-2.5-flash" - Re-run your evals or a sample of real prompts — output style, token usage and pricing can change between models.
- Check config outside code too: environment variables, feature flags, prompt-management tools, and fine-tuned model references.
- Deploy before September 24, 2025, and add the CI scanner so it cannot come back.
Also shutting down on September 24, 2025 (Google Cloud Vertex AI (Gemini Enterprise Agent Platform))
Questions
Is gemini-1.5-pro-002 deprecated?
Yes. Google Cloud Vertex AI (Gemini Enterprise Agent Platform) has deprecated gemini-1.5-pro-002. It was shut down on September 24, 2025.
When does gemini-1.5-pro-002 shut down?
September 24, 2025, according to Google Cloud Vertex AI (Gemini Enterprise Agent Platform)'s official deprecation notice.
What should I use instead of gemini-1.5-pro-002?
Google Cloud Vertex AI (Gemini Enterprise Agent Platform) recommends gemini-2.5-flash. Switch the model ID and re-test your prompts, since outputs, pricing and limits can differ.
What happens to requests to gemini-1.5-pro-002 after the shutdown?
Requests using the retired model ID fail with an error, so any code still calling it breaks. Update and deploy before the shutdown date.