Scheduled run spend cap: a per-call number can only lower it
A Sume schedule's default generation cap is $1.00. A per-run number is clamped to the lower of the request and the schedule cap, and 0 is rejected.

On a Sume schedule, a per-run generation_spend_cap_usd can lower the cap but never raise it: the API clamps a number above zero to the smaller of your request and the schedule's own cap, null runs without the automation ceiling, and 0 is rejected (Scheduled). If a schedule has no cap of its own, the default is $1.00.
How a request resolves
Assume a schedule with a $1.00 cap.
| Per-run value | Effective cap | Why |
|---|---|---|
| 0.25 | $0.25 | Lowered by the request |
| 1 | $1.00 | Equal to the schedule cap |
| 5 | $1.00 | Clamped to the schedule cap |
| 0 | 400 error | The API rejects 0 with 400 |
| null | No automation ceiling | Runs without the schedule cap |
An API-triggered run
Only schedules with api_trigger_enabled accept POST /v1/actions/{action_id}/runs; trigger_type is fixed at create time.
curl -sS -X POST "https://api.sume.com/v1/actions/$ACTION_ID/runs" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: weekly-teaser-2026-w41" \
-d '{"generation_spend_cap_usd": 0.25}'Other limits
| Limit | Value |
|---|---|
| input properties | 64 |
| input size | 2 MiB |
| Idempotency-Key length | 1 to 255 characters |
| list limit | 1 to 100, default 50 |
Practical use
Set the real ceiling on the schedule in the dashboard and use the per-run number only for cheaper one-off runs. Raising spend means editing the schedule, not the request.
The null caveat
null is the one value that removes the automation ceiling, so do not send it from an unattended client that you expect to stay capped. Wallet balance, generation admission and organization limits still apply, as the API-trigger page notes. Sending a bare number above zero is the safe way to tighten a single run.
Sources
Related posts
More in Agents
- Sume MCP avatar tools: 5 read-only and the paid create set
Hosted Sume MCP lists five read tools for avatars and avatar videos and a paid group for creates and previews. What OAuth mcp:read sees and the dry_run flow.
- What an agent should log when it calls Sume: ids yes, signed URLs no
Safe log fields for agents using the Sume API, CLI and MCP: request ids, job ids, status, sanitized media metadata. Never keys, signed URLs or transcripts.
- Run the Sume video agent from your backend with Agent Completions
POST /v1/agent/completions runs the same agent as the Sume Agents chat, with tools and media generation, and returns an async run receipt you poll or webhook.
- Safe automation for AI agents that call paid APIs
Keep agents read-only by default, keep secrets out of logs, and on hosted MCP send an idempotency_key, preview with dry_run, and cap with max_spend_usd.
Written by Sume