Gemini Omni Flash edit billed per input second vs Sume reserve
Runway bills Gemini Omni Flash video-to-video at 11 credits per input second, capped at 10 seconds. Sume reserves an edit from an 8s hint, not a probe.

Runway bills its gemini_omni_flash video-to-video at 11 credits per second of input video, capped at 10 seconds, plus 1 credit per reference image (its pricing page lists the 1.1 model separately). Sume's gemini-omni-flash-1.1 edit is billed by output second at provider list times 1.25, and because the output length is not returned, the reserve uses a duration hint that defaults to 8 seconds.
Runway numbers are from its pricing guide; Sume's from the Video Router docs, read 2026-10-01.
How does Runway count an edit?
Per the guide, the unit is the input clip: 11 credits for each second of input, up to 10 seconds, and 1 credit for each reference image. A longer input does not raise the charge beyond the 10-second cap.
How does Sume reserve an edit?
An edit sends no duration to the provider and the output follows the source clip. If you pass duration with video_url, it is only the reserve-estimate hint, default 8 seconds. The provider does not return an output duration for edits, so the reserve is a hint, not a probe of your file.
| Item | Runway `gemini_omni_flash` | Sume `gemini-omni-flash-1.1` |
|---|---|---|
| Billing unit | input second, cap 10 s | output second, by resolution |
| Reference images | 1 credit each | not combinable with an edit |
| Length signal | input clip length | duration hint, default 8 s |
| Margin | credits | provider list x 1.25 |
What can go wrong with a hint?
The reserve is an estimate set before the job runs. If your clip is far from 8 seconds, set duration near the real length so the reserve is close; do not treat the hint as a quote. Check the job result for the amount billed.
What should I do?
Trim the source to what you need before sending, set duration to its length, and read per-model pricing rows from the model catalog. For per-resolution costs of the same model see Gemini Omni Flash 1.1 at 360p.
Sources
Related posts
More in Pricing
- gpt-image-2.5 batch pricing: $4 image input, $15 output per 1M
OpenAI's batch rate for gpt-image-2.5 is $4.00 image input and $15.00 output per 1M tokens. Sume's docs describe a per-image reserve, not a batch tier.
- gpt-realtime-translate pricing: $0.034 per minute, and STT plus TTS
OpenAI lists gpt-realtime-translate at $0.034 per minute. Sume has no live translate line; STT 1.0 and TTS 1.0 are separate rates you add up yourself.
- Grok Imagine video price per second: xAI $0.05 and Sume's rate
xAI lists Imagine video from $0.05 per second. On Sume, grok-imagine-video-1.5 carries a list rate in code and bills at list x 1.25. The per-second math.
- Grok TTS at $15 per million characters vs Sume per-character TTS
xAI lists text to speech at $15.00 per 1M characters, or $0.015 per 1,000. Sume TTS also bills per transcript character, with a USD estimate before you run.
Written by Sume