Lovable AI Gateway
google/gemini-2.5-flash model retirement
RedirectedSubscribe to Lovable AI GatewayShare
On October 20, 2026, Lovable AI Gateway retired model google/gemini-2.5-flash. Calls using this model are no longer processed directly by it. Instead, Lovable AI Gateway redirects them and answers from a newer model.
What to use instead of google/gemini-2.5-flash
Lovable AI Gateway automatically sends calls to a replacement model. To update your integration, move to another model that the gateway lists.
Facts
- API
- Lovable AI Gateway
ai.gateway.lovable.dev - Model
google/gemini-2.5-flash- Released
- June 17, 2025 (models.dev)
- Kind
- Model retirement
- Takes effect
- October 20, 2026
- Calls after that day
- Answered by a newer version
- Source
- Model list
- Last updated
- Verified
- , against Lovable AI Gateway's own pages
Questions
When does this change take effect?
Since October 20, 2026, Lovable AI Gateway answers calls to the model google/gemini-2.5-flash from a newer version.
What happens to calls after October 20, 2026?
Lovable AI Gateway answers them from a newer version. The response can differ from what your code expects.
When was google/gemini-2.5-flash released?
google/gemini-2.5-flash was released on June 17, 2025, according to models.dev.
How do I find the calls this hits in my code?
Okapi reads your repository, finds the calls this change hits and opens a pull request with the fix. It never commits to your branches: every change comes as a pull request you review.
google/gemini-2.5-flash on other APIs 3
-
Vertex AI
gemini-2.5-flashModel retirement Stopped working -
OpenRouter
google/gemini-2.5-flashModel retirement Stopped working -
Gemini API
gemini-2.5-flashModel retirement Redirectsin 25 days
More from Lovable AI Gateway 10
-
google/gemini-2.5-flash-liteModel retirement Redirected -
google/gemini-2.5-proModel retirement Redirected -
google/gemini-3.6-flashModel retirement Redirectsin 13 days -
openai/gpt-image-1-miniModel retirement Stops workingin 25 days -
openai/gpt-5Model retirement Redirectsin 35 days -
openai/gpt-5-miniModel retirement Redirectsin 35 days -
openai/gpt-5-nanoModel retirement Redirectsin 35 days -
openai/gpt-4o-mini-ttsModel retirement Stops workingin 61 days -
google/gemini-3.7-flashModel retirement Redirectsin 83 days -
openai/gpt-4o-mini-transcribeModel retirement Stops workingin 112 days
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.