Cost of a 90-second Sume edit pipeline: trim, detach, filter, render
Trim is $0.02, audio detach $0.01, a filter encode $0.02, and a timeline render $0.10 per output minute rounded up. Two minutes of output adds up to $0.25.

A 90-second edit that trims a clip, detaches its audio, runs one filter encode and renders a timeline costs $0.02, $0.01, $0.02 and $0.20, for $0.25. The render is $0.10 for each output minute rounded up, so 90 seconds bills as two minutes.
The docs say to confirm these live in GET /v1/catalog, so treat the figures here as a reading from 2026-10-03, not a contract.
The line items
Prices are from the Sume errors and credits page (read 2026-10-03).
| Step | Price | Notes |
|---|---|---|
| video-trim | $0.02 per job | One trim |
| audio-detach | $0.01 per job | Splits audio from a clip |
| video-filter encode | $0.02 per encode job | The filter check is free |
| timeline-1.0 render | $0.10 per output minute, rounded up | Reserve is ceil(audio.duration_seconds / 60) |
| timeline-1.0 plan | Unbilled | POST /v1/timeline-1.0/plan |
| timeline-compose | $0.02 flat | Optional |
| timeline-audio | $0.01 flat | Optional |
Add it in integer cents
Use integers so there is no float drift, and use math.ceil for the render minutes.
import math
CENTS = {"trim": 2, "detach": 1, "filter": 2}
RENDER_PER_MIN = 10
def pipeline_cents(output_seconds, steps):
minutes = math.ceil(output_seconds / 60)
return sum(CENTS[s] for s in steps) + minutes * RENDER_PER_MIN
cents = pipeline_cents(90, ["trim", "detach", "filter"])
print(cents, f"${cents / 100:.2f}")Where it differs
Compose and audio steps each add a cent or two when used. A Format run also has the agent's own turn, which these flat prices do not cover, as in action runs and billable amounts. Read the actual spend from receipts, as in cost per row, and see how 61 seconds becomes two minutes.
Sources
Related posts
More in Pricing
- Video inspect transcribe: per-minute STT add-on, 10-minute cap
Adding transcribe true to a Sume video inspect adds $0.01 per audio-minute of your duration hint, one minute if omitted, up to 10 minutes.
- Video Router: what a request with no resolution or duration costs
Leave out resolution and duration and Sume prices a default. Wan 3.0 reserves a 1080p, 5-second clip. See each model's default and cost per clip.
- Video to transcript cost: audio detach plus STT, by minutes
Detach a video's audio for $0.01, transcribe it at $0.01 a minute. One-, three-, five- and ten-minute videos cost $0.02 to $0.11 at Sume list rates.
- Wallet needed to fill the Sume job queue, by plan
Filling Pro's 24 accepted job slots with 30-second Standard avatar clips reserves $132.48 up front; Scale's 120 slots reserve $662.40. Free has 6 slots.
Written by Sume