Gemini Omni API first-day checklist: billing, $10 window, $250 cap
Before your first Omni call on the Gemini API: link billing for Tier 1, know the $10 window and $250 cap, use the right model id, and test a 3-second 360p clip.

Before the first Omni call on the Gemini API, link a billing account (that is Tier 1), note the $10 spend window per 10 minutes and the $250 monthly cap, and use the model id gemini-omni-1.1-flash through the Interactions API. Start with a 3 second, 360p clip. Output is billed at about $0.10 per second of 720p video, and the free tier is not a safe assumption, so check the pricing page for your project.
The checklist
Each line below is drawn from a Google page I read on 2026-10-04: billing, rate limits, the Omni guide and pricing.
| Check | What the page says |
|---|---|
| Billing | Tier 1 needs a linked billing account |
| Model id | gemini-omni-1.1-flash, Stable on the models page |
| API surface | Interactions API |
| Spend window | $10 per rolling 10 minutes on Tier 1 |
| Monthly cap | $250; at the cap service pauses for all linked projects |
| Test clip | 3 to 10 seconds, 360p to 4K, 24 FPS |
| Aspect ratio | 16:9 or 9:16 only |
Mistakes to avoid
- Do not send temperature, top_p, stop sequences, system instructions or negative prompts; the guide lists them as unsupported.
- Do not pass a YouTube link as the source video; use a direct file.
- Do not trim your first edit test to more than 10 seconds; uploaded edit or extend clips must be 10 seconds or less.
- Do not assume the default
deliveryis a URL; base64 is the default, with about a 4 MB maximum, so requesturifor longer clips. - Do not rely on editing uploaded video in the EEA, Switzerland or the UK; Google lists it as unavailable there.
If you would rather not manage tiers
Sume's Video Router takes the same job with gemini-omni-flash-1.1, a different word order for the id, at provider list times 1.25 per second, with 3 to 10 second clips from 360p to 4K. Limits come from your plan's concurrency in Generation admission rather than from spend windows. Either way, run the cheap clip first.
Sources
- Google AI for Developers: Billing (read 2026-10-04)
- Google AI for Developers: Rate limits (read 2026-10-04)
- Google AI for Developers: Generate and edit videos with Gemini Omni Flash (read 2026-10-04)
- Google AI for Developers: Gemini Developer API pricing (read 2026-10-04)
- Google AI for Developers: Gemini models (read 2026-10-04)
Related posts
More in Developers
- Omni Flash prompts in English, captions in your language
Google says Omni fully supports English; other languages are unevaluated. Prompt in English, then add captions in your language with Sume's captions API.
- Gemini Omni Flash resolution: "4K" or "4k" on Sume
Sume accepts 4k as an alias of 4K for Gemini Omni Flash 1.1 and translates it to the lowercase token fal expects. Billed rate and Google's 4K caveat.
- Moving Veo scripts to Gemini Omni: an Interactions API checklist
Veo 3.1 previews shut down Oct 22. Omni uses the Interactions API, task values, base64 or uri delivery and different limits. A checklist for rewriting scripts.
- Generate a Python client from the Sume OpenAPI JSON
Point openapi-python-client at the live Sume OpenAPI document, regenerate on each release, and keep a thin wrapper for polling, retries and the data envelope.
Written by Sume