Five requests Omni Flash cannot take, and what to send instead
Gemini Omni Flash 1.1 on Sume refuses clips over 10 seconds, silent clips, audio references, 1:1 and 2K or 480p output. What to send instead for each.
Gemini Omni Flash 1.1 cannot make a clip over 10 seconds, cannot make a silent clip, cannot take audio references, cannot output 1:1, and offers only 360p, 720p, 1080p and 4K. Each has a catalog alternative; the table gives the one the Sume docs support.
Limit and alternative
| Need | Omni Flash 1.1 | Send instead | Price for 12 s at 720p / 1080p |
|---|---|---|---|
| 12 to 30 s in one request | 3-10 s only | wan-3.0 (2-30 s) or seedance-2.5 (4-30 s) | $1.50 / $3.00 Wan, $6.9336 / $17.0586 Seedance |
| Silent clip | generate_audio: false is rejected | A model whose catalog generate_audio allows an off value; Alibaba lists an audio toggle for wan3.0-video | Check the catalog |
| Audio reference | Image and video references only | Seedance 2.x, Wan 3.0, MiniMax H3 accept audio references | - |
| 1:1 output | 16:9 or 9:16 | Crop a render, or pick a model that lists 1:1 | - |
| 480p or 2K | 360p, 720p, 1080p, 4K | Wan or Seedance at 480p; MiniMax H3 bills 2K and 4K upscales | - |
How to check before you send
Read the live envelope with GET /v1/videos/models and filter on supported_durations, supported_resolutions and generate_audio. The catalog beats any table, including this one.
Keep Omni where it fits
None of this makes Omni a poor choice for short, sound-on, vertical or widescreen clips: an 8-second 720p one is $1.00. It makes it the wrong choice for long takes and for silent loops.
Sources
Related posts
More in Models
- Gemini Omni Flash 1.1 on Sume: spec sheet and billing in one page
Everything that ships for gemini-omni-flash-1.1 on Sume: 3 to 10 seconds, four resolutions, two ratios, always-on audio, reference limits, edit mode, billing.
- Gemini Omni rate limit: Google lists none, Sume lists them
Google's rate-limit page has no Omni or Veo row. It lists per-project RPM, TPM and RPD plus spend caps. Sume publishes per-key limits and concurrency by plan.
- GLM-5.3 reasoning cannot be turned off: cap the Sume run instead
Z.ai says GLM-5.3 always reasons, with low, high and max levels. What that means for run time and for a spend cap on a Sume agent run.
- GLM 5.3 Fast or Flash: which one does Sume list?
Sume's agent model list has GLM 5.3 Flash, not GLM 5.3 Fast. What Z.ai's GLM-5.3 page says and what the API's model field accepts.
Written by Sume