feat(google-vertex/google/gemini-omni-1.1-flash-preview): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for google-vertex/google/gemini-omni-1.1-flash-preview.

---

Note

Low Risk
Metadata-only addition with no runtime or application logic changes.

Overview
Adds a new provider catalog file for google/gemini-omni-1.1-flash-preview on Google Vertex (auto-generated by model-addition-agent).

The entry registers a preview, serverless video-mode model with a 1M-token context window, multimodal text/image/video/audio inputs, video-only output, and global pricing (input, text output, and video output token rates). Documentation links point at Google’s Gemini API pricing, Omni, and model docs.

^{Reviewed by Cursor Bugbot for commit b6b4402. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

Want higher recall? High effort reviews run extra passes and find more bugs. A team admin can switch effort levels in the Cursor dashboard.

^{Reviewed by Cursor Bugbot for commit b6b4402. Configure here.}

[cursor]

Omni 1.1 missing output modalities

Medium Severity

modalities.output lists only video, but Gemini Omni 1.1 Flash natively emits audio with video and returns text for conversational edits. The sibling gemini-omni-flash-preview catalog entry already records video, audio, and text. The incomplete list will hide this model from audio/text capability filters and understate what callers receive.

 

^{Reviewed by Cursor Bugbot for commit b6b4402. Configure here.}