# gemini-2.5-flash

From December 1, 2026, Gemini API answers calls to the model gemini-2.5-flash from a newer version.

On December 1, 2026, Gemini API will retire model gemini-2.5-flash. After that date, calls to model gemini-2.5-flash will not fail, but will be redirected automatically to answer from a newer model.

## What to use instead

Move calls to gemini-3.5-flash-lite before December 1, 2026.

- API: Gemini API (generativelanguage.googleapis.com)
- Model: gemini-2.5-flash
- Released: June 17, 2025 (models.dev)
- Kind: Model retirement
- Takes effect: December 1, 2026
- Calls after that day: answered by a newer version
- Calls it hits: `model gemini-2.5-flash`
- Source: [Deprecations page](https://ai.google.dev/gemini-api/docs/deprecations)
- Verified: November 6, 2026, against Gemini API's own pages
- Page: https://www.okapi.bot/models/gemini-api/gemini-2.5-flash/

## Gemini API's words

> Model: gemini-2.5-flash; Release date: June 17, 2025; Shutdown date: December 1, 2026; Recommended replacement: gemini-3.5-flash-lite (gemini-2.5-flash is no longer available in Google AI Studio; effective December 1, 2026, API requests to gemini-2.5-flash will automatically route to gemini-3.5-flash-lite)

Okapi finds the calls this change hits in your repo and opens the pull request with the fix: https://github.com/apps/okapi-agent