Skip to main content
Every agent has two server-enforced limits: a daily spend cap (soft pause) and an hourly action cap (hard pause). Both are configured per-agent. Neither can be exceeded — the runtime checks before each LLM call and before each mutating tool call.

​
Daily spend cap

PropertyValue
Default$5.00 (500 cents)
TypeSoft pause — auto-resumes
ResumeAt 00:00 in the workspace timezone (configurable)
StatusPAUSED_COST
User notificationEmail + any channels subscribed to on_pause
The runtime maintains agent_cost_ledger per (agent, day, provider, model). Before each LLM call, the CostGovernor computes estimated_cost = prompt_tokens × 1.2 × per-token price and refuses if ledger_today + estimated > cap. Refusal sets status=PAUSED_COST, files a COST_PAUSE pending item, and exits the cycle.

​
Hourly action cap

PropertyValue
Default60 actions/hour
TypeHard pause — requires human resume
StatusPAUSED_RATE
BackingRedis sliding-window counter
User notificationEmail + any channels subscribed to on_pause
An “action” is any mutating tool call (everything in the Mutating category in Rules and decisions). Read-only tools don’t count. The cap exists to prevent runaway loops — a misbehaving prompt that retries the same action 100 times gets stopped at 60.

​
80% warning

When daily spend crosses 80% of the cap, the agent fires a on_cost_threshold notification. The UI shows an “approaching cap” banner on the agent header. Configurable via the rule set: 
"notifications": {
  "on_cost_threshold_pct": 80
}

​
Model choice

ModelUseCost (relative)
claude-opus-4-7 (default)Planning loops, escalation triage, user-initiated chat1×
claude-haiku-4-5-20251001 (fast path)Routine event-triggered cycles~0.1×
gpt-4.1 (BYO)When llmProvider = BYO_OPENAIYour account’s pricing
Other claude-* (BYO)When llmProvider = BYO_ANTHROPICYour account’s pricing
The fast path is opt-in via the rule set: 
"runtime": {
  "use_fast_model_for_routine_cycles": true
}
Default true. Saves ~10× on the common (event-driven) path.

​
BYO key

Bring your own Anthropic or OpenAI API key. We never bill you for usage on the BYO path — your account is charged by the provider directly. See the full walkthrough: BYO Anthropic key.

​
Pro Max downgrade

If your workspace downgrades off Pro Max, all ACTIVE agents move to PAUSED_USER with reason "Plan downgraded — Pro Max required". The agent rows stay in the database — re-upgrade reactivates them with config intact, including rule sets, channels, data sources, and pending items. Memory notes and run history persist throughout.

​
Cost dashboard

Two views in the app:
  • /workspace/agent-costs — workspace-wide MTD total, sum of caps, projection.
  • /agents/{id}/costs — per-agent breakdown by day and model.
Cost dashboard

​
API

EndpointReturns
GET /api/v1/workspaces/{wid}/agent-costsWorkspace aggregate + per-agent rollup.
GET /api/v1/agents/{id}/costsPer-day breakdown, MTD vs cap, projection.