Runway Workflow as an endpoint vs a Sume Format over the API
Runway publishes a Workflow as an API endpoint from the Web App; Sume serves a saved Format at /v1/formats/{handle}/{slug}/runs. Setup and billing differ.

Runway lets an admin or editor publish a Workflow as an API endpoint with one click from the Web App, then a developer runs it from the Developer Portal or copies code with Get Code. Sume's equivalent is a Format: a saved recipe you call with POST /v1/formats/{handle}/{slug}/runs using an API key. The big differences are that Runway links two accounts and bills the Developer balance, while Sume uses one key with scopes and returns a typed result you define.
Setup and billing
| Question | Runway Workflow endpoint | Sume Format |
|---|---|---|
| Where you build it | Visually in the Web App, as nodes | SKILL.md and reference files, in the dashboard or Contents API |
| Who can publish | Admins and editors | The owning workspace; scopes formats:write |
| Account setup | Developer Portal and Web App accounts must be linked | One API key with formats:read and formats:write |
| Inputs and outputs | Labelled when publishing; an eye icon shows or hides each | input is free-form JSON; output_schema binds the result |
| Credits used | Developer account credits | Workspace wallet, capped per run in USD |
| Edits | Each change deploys immediately | version bumps per edit; the receipt shows which ran |
What comes back
A Format run returns a receipt with status_url, result_url, events_url and cancel_url. Statuses are queued, processing, then completed, failed, canceled or skipped. With an output_schema, output comes back in your shape and primary_output_url points at the headline file.
curl -sS -X POST "https://api.sume.com/v1/formats/acme/live-commerce/runs" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-8823-v1" \
-d '{
"instruction": "Vertical 9:16, no BGM.",
"input": { "product_url": "https://shop.example.com/p/8823" },
"output_schema": {
"name": "acme/live-commerce/v1",
"strict": true,
"schema": {
"type": "object",
"additionalProperties": false,
"required": ["full_video"],
"properties": { "full_video": { "$ref": "SumeMediaFile#" } }
}
},
"primary_output_key": "full_video",
"generation_spend_cap_usd": 120
}'Edits do not touch a run in flight
Runway says each change to a published endpoint deploys immediately. On Sume, editing a Format's package never touches a run that is already in flight, because each run reads the package it started with. The version on the receipt is the proof of which recipe ran.
Pick by who builds
- Visual nodes built by a creative team, called by a developer: Runway's published Workflow.
- A recipe an agent follows, with a schema you own and webhooks or polling: a Sume Format.
- Whichever you choose, read how credits or dollars are charged before the first call.
Sources
Related posts
More in Comparisons
- Runway workspace workflows vs Sume Format grants for partners
Runway Agent runs workflows shared with you but will not edit them. Sume shares a Format with another workspace by grant, and the caller pays. The rules.
- Seedance 2.5, Wan 3.0 and Omni Flash: where each one is sold
Runway lists seedance2_5, wan3 and gemini_omni_flash_1.1 as API ids, Luma hosts Seedance 2.5, and Sume routes all three. How to compare.
- Seedance 2.5: fal's 30 s at 720p listing vs Sume's catalog limits
fal.ai/models says Seedance 2.5 is a native 30-second clip at up to 720p. Sume's catalog lists 4 to 30 s at 480p, 720p and 1080p. Read the live values.
- Seedance 2.5 per second: Runway 20/30/68 credits vs Sume's rates
Runway lists Seedance 2.5 at $0.20, $0.30 and $0.68 per second at 480p, 720p and 1080p; Sume bills $0.2687, $0.5778 and $1.4216 for a 10-second clip.
Written by Sume