Estimate a video render cost before you pay: Sume timeline plan
POST /v1/timeline-1.0/plan returns billable minutes, an estimated cost and a filtergraph summary without a job, a reserve or a media download.

You can check what a Sume timeline render will cost before you pay by calling the plan endpoint. POST /v1/timeline-1.0/plan runs the schema check, the Sume media host check and the compiler, then returns billable_minutes, estimated_cost_usd_micros, duration_seconds, segment_count and a filtergraph_summary. It creates no job, reserves no credits and downloads no media, and it needs no Idempotency-Key.
What the plan does and does not tell you
The public render rate is $0.10 per output minute, rounded up, so billable_minutes is the number to multiply.
| Question | Plan | Render |
|---|---|---|
| Creates a job | No | Yes |
| Reserves credits | No | Yes |
| Idempotency-Key | Not required | Required |
| Downloads media | No | Yes |
| Predicts short-source pad or loop warnings | No | Reports them |
| Catches schema, host and compiler errors | Yes | Yes |
Run it on the documented example
Swap in artifact URLs from your own workspace. For a 24-second output the plan should report one billable minute, which is $0.10.
curl -X POST https://api.sume.com/v1/timeline-1.0/plan \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"audio": {"mode": "silence", "duration_seconds": 24},
"video": [
{"source_url": "https://media.sume.com/artifacts/artf_demo/intro.mp4", "start": 0, "duration": 8},
{"source_url": "https://media.sume.com/artifacts/artf_demo/talk.mp4", "start": 8, "duration": 16}
]
}'Where it earns its place
Because a plan cannot see the files, the final render can still warn that a short source was padded or looped. Treat the estimate as the price and the warnings as the quality check.
- Batch jobs: sum billable_minutes across all plans before you submit anything.
- Agents: show the estimate to a person, then render on approval.
- Debugging: transition and slot errors come back at plan time, before you spend.
Budgeting a batch with plans
For a batch of 50 renders, call plan 50 times and add up billable_minutes. Each plan is free and does not reserve anything, so you can rebuild the batch as often as you like. Multiply the total by the $0.10 public rate, then compare it with your balance before you submit.
Plans are also a cheap test for agents. An agent that composes a timeline from a brief can plan it, show the minutes and the cost, and only then submit the render with an Idempotency-Key. The plan is not a reservation, so a render submitted later can still be refused if the balance changed in the meantime. Note that a plan does not download media, so a dead URL on the Sume host can pass a plan and fail the render. Probe your sources first if the batch is large.
Sources
Related posts
More in Media tools
- Kling motion control job done: a signed Python webhook receiver
Submit a Sume Kling 3.0 motion-control job with mode webhook, then verify the HMAC signature in Python, reject an empty secret and answer fast. Runnable code.
- Loop a 30-second music bed under a 3-minute Reel: the body
A short bed can cover a 180-second Reel with soundtrack.loop, duck_db and a fade-out. One Timeline 1.0 body, the 3-minute bill, and the limits to respect.
- MAI-Voice-2.1 is not on Sume: make talking clips with Sume TTS
Microsoft MAI-Voice-2.1 launched 2026-10-01 but Sume does not list it. Here is the path that ships: Sume TTS audio, then H3 Max lip sync on a still.
- MiniMax H3 Max lip sync API: your first clip in Python
Submit a still and a Sume-hosted audio file to POST /v1/minimax/h3-max/lip-sync, poll the job, and read the result. Python stdlib, with the 5 to 14.8 s rule.
Written by Sume