Hi, I’m troubleshooting Gemini 3 Pro Image access through the Gemini Developer API.gemini-3-pro-image works through v1beta, but is not listed or callable through v1.
What I have verified:
-
I tested two separate API keys from different Google Cloud projects.
-
One project is a paid Gemini API project with active prepaid credit.
-
The second key is a newly created, service-account-bound authorization key.
-
Both keys can list and call image models through
v1beta. -
Both keys list
gemini-3-pro-imageinv1beta. -
Both keys can use
gemini-3-pro-imagesuccessfully throughv1beta. -
Through
v1, both keys can list Flash image models, butgemini-3-pro-imageis absent. -
A direct
v1call returns:
models/gemini-3-pro-image is not found for API version v1, or is not supported for generateContent. Call ModelService.ListModels to see the list of available models and their supported methods.
The requests use the stable model ID gemini-3-pro-image, not gemini-3-pro-image-preview, and request a fresh 1K 4:5 image. This is not a multi-turn or 2K/4K request.
Example failing endpoint:
POST https://generativelanguage.googleapis.com/v1/models/gemini-3-pro-image:generateContent
Equivalent working endpoint:
POST https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image:generateContent
Google’s documentation describes gemini-3-pro-image as stable/GA and indicates models should be supported in both v1 and v1beta.
Is this expected behaviour for Gemini 3 Pro Image on the Gemini Developer API, a rollout limitation, or a project-level access issue? Is there any action required to make the stable model available through v1 generateContent?
Thank you.