Runway Agent skills vs a saved Sume Format you call by API
A Runway Agent skill is saved instructions you trigger with / in a chat. A Sume Format is a saved recipe your backend calls by handle and slug. Which fits when.

A Runway Agent skill is a saved set of instructions, up to 5,000 characters, that you trigger by typing / in the Agent composer, so it is a tool for a person working in a chat. A Sume Format is a saved production recipe that your own backend calls over HTTP by handle and slug, so it is a tool for code. If a human steers each step, a skill fits; if a service starts the job and nobody is watching, call a Format.
Side by side
Both save a repeatable workflow so you stop re-typing it. They differ in who starts the work and what comes back.
| Question | Runway Agent skill | Sume Format |
|---|---|---|
| Where it is saved | Skills menu in the Agent composer | Format library, or the Contents API |
| Size of the instructions | Up to 5,000 characters | A SKILL.md plus reference files; no cap beyond 100 MiB per file |
| Sharing | Private, or Share with workspace | Team handle; grants to other workspaces |
| How it starts | Type / and pick the skill by name | POST /v1/formats/{handle}/{slug}/runs |
| Who is in the loop | Skill checks in with you along the way | Unattended: approvals are pre-granted |
| Your inputs | Details typed next to the skill | input object: up to 64 top-level keys, 2 MiB |
What a Runway skill is
Runway's page lists built-in skills (Ad Campaign, Commercial, Mood Board, Motion Graphic, Resize Image, Social Thumbnail, UGC Video, Workflow) and a New Skill option. Each skill breaks its task into steps and checks in with you. Runway calls skills starting points, not scripts: you can redirect Agent at any step.
What a Sume Format adds
A Format run boots a fresh sandbox with the Format's package on disk, follows the recipe, and returns one receipt. The receipt carries the Format version that actually ran, so a later edit never rewrites history. Your own words go in instruction and your data in input, which the agent reads as data and not as instructions.
The catalog is callable without authoring anything. Any key with formats:write can post to the sume handle.
curl -sS -X POST "https://api.sume.com/v1/formats/sume/sume-product-commercial/runs" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: sku-1042-v1" \
-d '{
"instruction": "Vertical 9:16 hero clip, no captions.",
"input": { "product_url": "https://shop.example.com/p/1042" },
"generation_spend_cap_usd": 25
}'Which one to use
- Use a skill when you are in the chat, want to review each step, and the output goes to you.
- Use a Format when an order, a webhook or a cron job in your own system should start the video and read back a URL.
- Keep the recipe in one place. If you maintain both, the Format is the copy that code can version, because every edit bumps its version.
Sources
Related posts
More in Comparisons
- Runway Agent UGC and Commercial skills vs Sume catalog Formats
Runway's UGC Video and Commercial skills run in an Agent chat. Sume's sume-close-camera-ugc and sume-product-commercial Formats are called by slug from code.
- Runway API credit rates for a 10-second clip, next to Sume's rows
At $0.01 per credit, Runway's API lists gen4.5 at $1.20 for 10 seconds and Veo 3.1 at $4.00. Sume rows: Wan 720p $1.25, H3 Max 768p $1.00. Not like for like.
- Runway enterprise exception requests vs Sume's queue-first admission
Runway's docs mention enterprise exception requests for higher volume. Sume takes extra jobs as queued and sets concurrency by plan. How to plan a big batch.
- Runway API model list vs the Sume video catalog: what overlaps
Runway's API lists Seedance 2.5, Wan 3.0, MiniMax H3, Grok Imagine Video 1.5 and Gemini Omni Flash. Which of those ids exist on Sume, and which do not.
Written by Sume