Managed Agents budget_reached vs Sume generation_spend_cap_usd
A Managed Agents session budget caps spend at list rates and pauses with budget_reached. Sume's generation_spend_cap_usd is a separate required cap.
They are two separate ceilings. A Claude Managed Agents session budget caps the session's spend at public list rates and pauses it with budget_reached; Sume's generation_spend_cap_usd caps generation spend on a Sume Agent Completion in dollars. Neither is documented as reading the other.
The Anthropic fact is from its release notes (entry dated 2026-08-07); Sume facts from Agent Completions, read 2026-10-01.
What does the session budget do?
Per the release notes it is a hard cap on a session's spend, priced at public list rates. A session that reaches it pauses with the budget_reached stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start.
What does generation_spend_cap_usd do?
It has no default: omit it and the request fails with 400 invalid_request. The docs call it the substitute for the interactive spend-approval prompt, which a backend caller does not have, and say to set it to the most you will spend on a single run. The receipt echoes it as generation_spend_cap_usd_micros under usage.
| Managed Agents session budget | Sume generation cap | |
|---|---|---|
| Unit | Session spend at public list rates | Dollars, generation_spend_cap_usd |
| Required | Not stated in the notes | Yes, no default |
| At the limit | Pauses, budget_reached | See the completions page for the run's outcome |
| Recorded | Stop reason | Echoed in usage on the receipt |
Which one stops a run first?
Whichever limit the run reaches first, and the two are measured differently (list-rate session spend versus Sume generation spend), so they are not directly comparable. A run that spends mostly on model tokens meets the session budget; one that spends on generations meets the Sume cap. Set both deliberately, and size the Sume cap from the API pricing page as the docs suggest.
Is there a tighter bound inside a script?
Yes for MCP script_run: it is bounded by timeout_seconds, max_calls and max_paid_calls. Related reading: paid MCP calls under auto permissions.
Sources
Related posts
More in Pricing
- Workers AI paid models 20/min, 50 with prepaid vs Sume plans
Cloudflare lifts paid Workers AI models from 20 to 50 requests per minute with prepaid credits. On Sume, top-ups do not raise concurrency; the plan does.
- Captioning 100 short videos: Sume's $20 per-job price vs minute packs
Sume's caption job is a flat $0.20 for a video up to 60 seconds, so 100 videos cost $20 at any length under a minute. Submagic's minute packs give $3 to $17.
- Creatify Ad Clone credits: 12 per 5 seconds of output
Creatify bills Ad Clone at 12 credits per 5 seconds of output. Sume Avatar Video uses a named quality tier instead, with previews before a full render.
- Creatify Aurora 2k credits per second: 2.8, audio up to 14.375 s
Creatify Aurora 2.0 bills 0.4 to 2.8 credits per second by resolution, and 2k only works for audio up to 14.375 s. Sume Avatar Video renders at 720p.
Written by Sume