Budget warning
Notifies an operator when the configured condition is met; it does not allow or reject requests.
Cost governance
Control LLM spending with budgets your organization sets.
Organization admins allocate monetary budgets to organizations, teams, users, and widgets, configure warnings, and choose soft or hard limits for supported requests.
Soft limit
Requests covered by the policy continue with a warning at the applicable soft limit.
Hard limit
Rejects requests covered by the policy when the hard limit is reached.
Policy coverage
Set LLM budgets by organization, team, user, or widget.
Enforcement requires a supported request path and an active policy. Other paths can continue without a budget check.
Available policy scopes
Where your teams use agents
Agents used by signed-in teams: Supported authenticated workspace and external-agent requests can apply organization, team, and user policies.
Agents in website widgets: Supported widget requests can apply organization and widget policies.
Organization admins choose budget policies. Access to policy and usage information follows organization permissions.
Practical guide: governance and cost controls for AI agentsCompare cost and quality, account for retries and review time, and confirm enforcement.Usage and cost
Review spending by provider, AI model, and request owner where captured. Agent and workspace reporting provides visibility, not separate budget enforcement.
Activity records
Investigate runs and errors using the activity records captured by each supported request path.
From policy to review
Budget, launch, and respond.
- 01
Allocate a budget
Choose who it covers, the spending limit, and the period.
- 02
Prepare the rollout
Set warnings and limits. Confirm the workflow enforces them.
- 03
Respond to spending
After a hard-limit rejection, retry once an authorized operator changes the policy or the budget period resets. Requests are not queued for approval.
Usage and cost context
Turn usage records into decisions.
Finance
Compare reported spending with allocations and adjust budgets.
Operations
Use captured activity and errors to investigate repeated failures.
Platform teams
Confirm AI model access and policy enforcement before rollout.
When a team reaches its budget
Fictional example — not a customer result or savings guarantee.
Set a policy
Example Company sets monthly limits: $400 soft for the team, $1,000 hard for the organization. Warnings are configured separately.
Review the warning
The operator checks recorded spending by agent or workflow, then adjusts the team policy or rollout—or leaves it unchanged.
Apply the limits
At the team’s soft limit, covered requests continue with a warning. At the organization’s hard limit, new covered requests are rejected.
FAQ
LLM budget questions
Yes. Supported scopes are organization, team, user, and widget. Organization admins choose the policies; enforcement depends on the supported request path.
Covered requests continue with a warning at a soft limit. At a hard limit, they are rejected. Retry after an authorized operator changes the policy or the budget period resets; requests are not queued for approval.
Supported authenticated workspace and external-agent requests can apply organization, team, and user policies. Supported widget requests can apply organization and widget policies. An active policy is required; other paths can continue without a budget check.
Review available records by provider, model, and request owner. Managed access shows billed costs; your own provider key shows provider-reported costs. Coverage and timing depend on the request path.
Keep learning
Plan your spending controls
Plan your next rollout.
Explore budgets, warnings, and supported limits for the agents your teams want to use.