Gemini app Omni video needs a Google AI plan; the API is separate

In the Gemini app, Omni video generation needs a Google AI plan for personal accounts or a qualifying Google Workspace license for work and school accounts, and it is not available to users under 18. Calling the model through an API is a separate path with its own paid-tier pricing. On Sume, you reach it as gemini-omni-flash-1.1 in the Video Router.

Facts are from Gemini Apps Help, Google's Omni launch post and the Gemini API pricing page, read on 2026-10-03.

App access versus API access

The app is a consumer surface with plan gating and upload rules. Google's launch post lists the Gemini app and Flow for AI Plus, Pro and Ultra subscribers, and YouTube Shorts and YouTube Create for free for users 18 and over. The API pricing page lists Omni as paid-tier only.

Upload limits to plan around

Gemini Apps Help says uploads are unavailable in the EEA, Switzerland, the UK and some US states. Sume's reference limits differ: up to 10 reference images and up to 3 reference clips of 3 seconds each. If you produce at volume or need a repeatable pipeline, a job API with polling and webhooks is easier to automate than a chat app.

The same task on Sume

There is no plan to sign up for on Sume. You send a request with an API key and get an async job back; billing is by output seconds. The Video Router docs show all fields.

curl -X POST https://api.sume.com/v1/video-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: omni-app-vs-api-001" \
  -d '{
    "model": "gemini-omni-flash-1.1",
    "prompt": "A paper boat drifts down a rain gutter, close-up, soft grey light.",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "mode": "async"
  }'