Skip to main content

Product use cases · Screen production · Video

Ship an episode a day without losing the cast between them.

Stage a 9:16 elevator scene between two fictional adults: a woman in an emerald jacket and a man in a charcoal shirt. Use an establishing shot, her line, and his reply.

Best for
Vertical drama studios and short-form series teams producing episodes on a fixed daily or weekly cadence.
What you get
A per-episode cost line, a cast plate that outlives the episode, and a batch you reconcile in one request instead of tracking shot by shot.

Concept illustration

A creative brief to try

Block an elevator exchange for mobile

  1. 01

    Keep a separate identity reference for each character. Board a two-person elevator shot and fix who stands on each side.

  2. 02

    Make her close-up for the first line and his close-up for the reply. Specify the speaker and the listener in each shot.

  3. 03

    Review all three frames, then animate one speaking turn at a time. Add or check dialogue timing in your editor.

Before you keep the result

Check faces, clothing, left-right positions, and whose mouth moves. Keep heads and captions inside the vertical frame.

Start with your own reference images, follow the scene plan and review each result.

Open this scene in the Playground →

Recommended models

168 matching models

Matches use the tasks and required capabilities published in the catalogue. Availability and current prices come from each model page.

Reference to video
18
from $0.011 / output second
Seedance 2.0 Mini · Reference to Video →
Image to video
56
from $0.011 / output second
Seedance 1.5 Pro · Image to Video →
Video extension
33
from $0.011 / output second
Seedance 1.5 Pro · Video Extend →
Text to image
61
from $0.0018 / image
GPT Image 2.5 Sunburst · Text to Image →

What one run costs

Worked out from the live catalogue, at the settings named under each figure.

Seedance 2.0 Mini · Reference to Video
$0.0548
5 × $0.011 · output seconds · lowest tier
Seedance 1.5 Pro · Image to Video
$0.056
5 × $0.0112 · output seconds · lowest tier
Seedance 1.5 Pro Spicy · Video Extend
$0.06
5 × $0.012 · output seconds · lowest tier

Catalog estimates refresh hourly. Check the estimate for your settings before running; final charges follow the model’s usage and billing policy.

How to build it

Estimate each planned shot with its own model and settings, then add those estimates to the episode budget. A signed quote is tied to one request and lasts 5 minutes. Keep cast originals in your own storage, submit the shots as separate tasks and reconcile their IDs against the episode plan.

  1. 01

    Price the run before it exists

    POST/api/v1/jobs/quote

    The same validation and admission rules as creating the task, except nothing is created and no money is held. The signed quote lasts five minutes.

  2. 02

    Ask for an upload ticket

    POST/api/v1/common/upload-url

    The ticket is valid only for the byte count you declared: JPEG, PNG, WebP and GIF up to 10 MiB each. Media that already has a public HTTPS URL skips this step entirely.

  3. 03

    Commit the uploaded file

    POST/api/v1/files/{fileId}/commit

    The commit checks the bytes and hands back a spicy:// reference, which is what a model's media fields accept. Committing the same file again changes nothing.

  4. 04

    Create the task

    POST/api/v1/jobs/createTask

    202 means accepted, not finished. Send an Idempotency-Key, and if the price must not move, send the jobs/quote result together with the amount you agreed to.

  5. 05

    Sweep the whole batch

    GET/api/v1/jobs

    One request returns the tasks this key created, newest first, up to 100 per page over a window of at most 92 days. It carries status only — no prompt, no output — so a finished item is still read back by its task ID.

  6. 06

    Move the file into your own storage

    POST/api/v1/common/download-url

    Mint a short-lived download URL for the output and copy it into your own bucket within the same job. Results stay on our CDN for 14 days.

Copy a request

This example starts with the scene described on this page. Fields come from the selected endpoint’s schema. Replace any example.com reference URL with your own image or committed file URI before sending.

Seedance 2.0 Mini · Reference to Video →

Where this usually snags

Platform behaviour that is cheaper to design around than to discover in production.

  • Aspect ratio is a list, not a number

    Resolution, aspect ratio and length come from each endpoint's own input schema as a closed set, and extra properties are refused. Check that the frame you ship in is on that list before you pin an endpoint to a format.

  • Without a key, a re-send is a second run

    Every write endpoint accepts an Idempotency-Key and remembers it for 24 hours. Leave it out and a batch script that re-sends after a timeout has created two tasks and will pay for both.

  • Give the key a ceiling before it ships

    Every API key carries a daily, a monthly and a lifetime spend cap. Set them when you create the key: a leaked key without one spends the balance, not the budget.

Launch checklist

  1. 01Estimate each planned shot with its own model and settings, then add those estimates to the episode budget. A signed quote is tied to one request and lasts 5 minutes. Keep cast originals in your own storage, submit the shots as separate tasks and reconcile their IDs against the episode plan.
  2. 02Keep the versioned character originals in your own storage and reuse accessible HTTPS references. Temporary uploads last 1 day, so refresh them when needed. Record reference order and settings for comparison, then check the face, hair and identifying details in each result; repeated inputs can still produce variation.
  3. 03Check the frame options on an endpoint before pinning it — aspect ratio is a closed set in each endpoint's own schema, and 9:16 is not offered everywhere.
  4. 04Give the production key a monthly cap so one runaway episode cannot spend the season.

Models that match this workflow

Explore model families for this workflow. Open a model page to review its inputs, pricing and current availability.

Frequently asked questions

168 published models match the listed tasks and required capabilities. Compare their inputs, examples, availability and current prices before choosing one.

About this workflow

Estimate each planned shot with its own model and settings, then add those estimates to the episode budget. A signed quote is tied to one request and lasts 5 minutes. Keep cast originals in your own storage, submit the shots as separate tasks and reconcile their IDs against the episode plan. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.