Scheduled Sume agent runs: the $1.00 default cap and min(request, cap)
A Sume schedule saves a spend cap, defaulting to $1.00 when unset. An API trigger can lower a run's cap but never raise it past the saved one.
A schedule has its own saved cap, and an API-triggered run is clamped to the smaller of the request and that cap. If the schedule does not set one, the docs give a default of $1.00. So a trigger can only lower what a run may spend. Raise the saved cap on the schedule itself if the work needs more, and do it on purpose.
How the cap shows up
A run also reports what it did. usage.billable_amount_usd_micros is the generation spend of that run, and generation_spend_cap_usd_micros is the ceiling that applied. usage is null when Sume could not read the spend, which is different from 0.
| Case | Saved cap | Request cap | Cap that applies |
|---|---|---|---|
| No request cap | Set on the schedule | none | Saved cap |
| Lower request | Set on the schedule | Below the saved cap | The request |
| Higher request | Set on the schedule | Above the saved cap | Saved cap |
| Nothing saved | Unset | none | $1.00 default |
Two limits to remember
The receipt figure excludes the agent's own LLM turn, which bills the separate Agent wallet, and GET /v1/usage is the authoritative record. Read Runs and results before you build a cost alert on billable_amount_usd_micros alone.
A schedule that is still running when the next fire arrives does not stack: the new run has status skipped and skip_reason of previous_run_active.
Check the docs before you ship
Sume's limits and field names change faster than blog posts do. Read the linked docs pages for the current request fields before you ship, and send a dry_run or a low spend cap on your first real call.
Sources
Related posts
More in Agents
- script_run budget stop: split the batch and wait outside the script
A Sume script_run budget stop (timeout, call or paid budget) means the script asked for more than allowed. Split it, or return job ids and wait outside.
- script_run on Sume MCP: what the sandbox cannot call, and its budgets
Sume's script_run tool runs JavaScript that calls other tools with await sume.call. It has 5 to 55 second timeouts, call budgets, and no discovery tools.
- Seedance video agent in ChatGPT and Claude: Sume MCP compared
InfoseekAI put a Seedance video agent into ChatGPT and Claude over MCP on Oct 1, 2026. What a hosted MCP server like Sume's gives you instead, and when.
- Sume skipped run with previous_run_active: what it means, what to do
A scheduled Sume run is skipped with skip_reason previous_run_active when the last one is still going. It is not billed work. How to detect it and avoid it.
Written by Sume