Gemini API
veo-3.1-fast-generate-preview model retirement
Stopped workingSubscribe to Gemini APIShare
Google retired model veo-3.1-fast-generate-preview on October 22, 2026. Calls specifying this model fail since that date. The shutdown affects requests sent to generativelanguage.googleapis.com that rely on this preview version.
The error you get
What Gemini API answers a call to veo-3.1-fast-generate-preview once the model is gone, as recorded from real responses:
{"error":{"code":404,"message":"This model models/veo-3.1-fast-generate-preview is no longer available to new users. Please update your code to use a newer model for the latest features and improvements.","status":"NOT_FOUND"}}{"error":{"code":404,"message":"models/veo-3.1-fast-generate-preview is not found for API version v1beta, or is not supported for generateContent. Call ModelService.ListModels to see the list of available models and their supported methods.","status":"NOT_FOUND"}}What to use instead of veo-3.1-fast-generate-preview
Move to gemini-omni-1.2-flash, which is the replacement recommended by Google.
In Gemini API's words
Model: veo-3.1-fast-generate-preview; Release date: October 15, 2025; Shutdown date: October 22, 2026; Recommended replacement: gemini-omni-1.2-flash
Facts
- API
- Gemini API
generativelanguage.googleapis.com - Model
veo-3.1-fast-generate-preview- Kind
- Model retirement
- Takes effect
- October 22, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Gemini API's own pages
Questions
When does veo-3.1-fast-generate-preview shut down?
Calls to the model veo-3.1-fast-generate-preview on Gemini API stopped working on October 22, 2026.
What happens to calls after October 22, 2026?
They have failed since October 22, 2026.
What error does veo-3.1-fast-generate-preview return once it is shut down?
Gemini API answers HTTP 404: "This model models/veo-3.1-fast-generate-preview is no longer available to new users. Please update your code to use a newer model for the latest features and improvements.". Send another model to fix it.
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.
veo-3.1-fast-generate-preview on other APIs 1
-
Vertex AI
veo-3.1-fast-generate-previewModel retirement Stopped working
More from Gemini API 10
-
gemini-1.0-flashModel retirement Stopped working -
gemini-1.0-proModel retirement Stopped working -
gemini-omni-flash-previewModel retirement Stopped working -
veo-3.1-generate-previewModel retirement Stopped working -
veo-3.1-lite-generate-previewModel retirement Stopped working -
gemini-2.5-flash-native-audio-preview-12-2025Model retirement Stops workingin 11 days -
gemini-2.5-flash-preview-ttsModel retirement Stops workingin 11 days -
gemini-2.5-pro-preview-ttsModel retirement Stops workingin 11 days -
gemini-3.1-flash-live-previewModel retirement Stops workingin 11 days -
gemini-3.1-flash-tts-previewModel retirement Stops workingin 11 days
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.