apiwatch

All changes / Google

Silent model

Since October 8, 2026, Google routes Gemini API requests for the deprecated gemini-3.5-flash to gemini-3.6-flash.

Took effect · Gemini API model gemini-3.5-flash

Reviewed against the vendor source on Nov 11, 2026 (AI-assisted review). Key facts are re-checked against the source daily.

What changes

The October 8, 2026 Gemini API changelog says gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash, that it is no longer available to select in Google AI Studio, and that API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Requests keep working, but they are served by a different model. The deprecations page lists gemini-3.5-flash (released May 19, 2026) with shutdown date N/A and gemini-3.6-flash as the replacement, and says the endpoint is not shutting down. Google's Gemini 3.5 guide describes gemini-3.6-flash as a direct replacement with reduced token usage and lower output pricing.

Silent: No error. Behavior, results, or cost change quietly.

What to do

Change the model string from gemini-3.5-flash to gemini-3.6-flash (the model already serving your requests) or gemini-3.8-flash, which the changelog also names. Re-run your evals on outputs, token usage and cost, since results already come from gemini-3.6-flash.

Strings to search for

gemini-3.5-flash

Not affected (matches inside these are ignored): gemini-3.5-flash-lite

Source

https://ai.google.dev/gemini-api/docs/changelog