Skip to contentOceanToken

Video render time

How long each video model takes measured on OceanToken

179 timed clips across 7 video models, October 15, 2026 to November 12, 2026. A setting is shown only once it has at least 5 timed clips.

Quickest clip

51 s

Veo 3.1 Lite
6 s clip, 720p

Typical clip

173 s

Median across the 17 settings below

Upscaled vs native

+60 s longer to render, typically

Price per second 19% lower

Upscaled or native

An upscaled model renders the clip at a lower resolution and enlarges it. At normal viewing size, on a phone or in a web player, the two are hard to tell apart; zoomed in to the pixel, fast motion, skin and hair, and fine texture can look smeared or over-sharpened. Composition, motion, finger counts and spelling come from the base model, not from the upscaling.

ModelSettingMedian timeFrame deliveredFrom
NativeUpscaledNativeUpscaledNativeUpscaled
Seedance 2.05 s clip, 720p181 s219 s1280×7201256×720not the standard frame$0.14/s$0.11/s
Seedance 2.0 Fast5 s clip, 720p115 s197 s–1256×720not the standard frame$0.098/s$0.085/s

Every setting measured

Quickest first. Time runs from submitting the job to the finished clip being ready to download.

ModelSettingMedian time9 in 10 withinFrame deliveredFromClips
Veo 3.1 Lite6 s clip, 720p51 sneeds 10 clips–$0.027/s5
Grok Imagine Video5 s clip, 720p66 sneeds 10 clips–$0.070/s5
Seedance 2.0 MiniCompare4 s clip, 480p99 s134 s864×496$0.028/s42
Seedance 2.0 Fast4 s clip, 480p100 s128 s864×496$0.045/s14
Seedance 2.0 Fast5 s clip, 720p115 sneeds 10 clips–$0.098/s5
Seedance 2.0 MiniCompare5 s clip, 720p121 sneeds 10 clips–$0.061/s5
Kling v3.0 Standard5 s clip, 720p122 sneeds 10 clips–$0.080/s5
Seedance 2.0 Mini UpscaledCompare4 s clip, 720p166 s180 s1256×720not the standard frame$0.053/s15
Seedance 2.5Compare4 s clip, 480p173 s298 s854×480$0.10/s13
Seedance 2.0Compare5 s clip, 720p181 s252 s1280×720$0.14/s12
Seedance 2.0 Fast Upscaled5 s clip, 720p197 sneeds 10 clips1256×720not the standard frame$0.085/s6
Seedance 2.0Compare4 s clip, 480p200 s271 s864×496$0.067/s12
Seedance 2.0 UpscaledCompare4 s clip, 720p211 s278 s1280×720$0.11/s12
Seedance 2.0 UpscaledCompare5 s clip, 720p219 sneeds 10 clips1256×720not the standard frame$0.11/s7
Seedance 2.5 UpscaledCompare4 s clip, 720p239 s336 s1280×720$0.19/s11
Seedance 2.0 Upscaled 4kCompare4 s clip, 4K246 sneeds 10 clips3840×2160$0.55/s5
Seedance 2.5 UpscaledCompare5 s clip, 720p248 sneeds 10 clips1278×720not the standard frame$0.19/s5

On customer traffic, last 30 days

Every video job our customers sent, counted only where a setting had at least 30 jobs from at least 5 different customers. Refused means the model maker’s content review declined the prompt or the clip.

ModelSettingSuccessRefusedMedian time9 in 10 withinFrame as askedJobs
Seedance 2.0 Mini480p, up to 5 s100%0%122 s141 s–77
Seedance 2.0 Mini480p, 6–10 s100%0%144 s173 s–52

Time, not looks

This page answers how fast and at what frame a model delivers. For which clips people prefer, see the human-preference votes of Artificial Analysis Video Arena.

How we measure

These are our own test jobs through the OceanToken API, not customer traffic: text-to-video prompts at the resolution and length shown, 16:9 unless stated. Each job is timed from submitting it to the first status check that reports the finished clip (we check every 5 seconds), so queueing at the model maker counts. Failed and refused jobs are not timed. A setting needs 5 timed clips to be shown, and the “9 in 10” figure needs 10. Output frames are read from the delivered files. Render time changes with the time of day and the maker’s load, so yours may differ.

Text models: output speed and first token 

Render with any of these models on one API key