Billing & Limits
Track usage, manage spending limits, and optimize costs across your organization.
The billing dashboard provides full visibility into your organization's usage and costs. Use it to track API calls, token consumption, and storage; set spending limits per workspace; and identify cost optimization opportunities.
Usage Dashboard
Navigate to Admin -> Billing to access the usage dashboard. It displays three primary metrics.
API Calls
Total number of endpoint triggers and pipeline executions across your organization, broken down by workspace and app.
Token Usage
Input and output tokens consumed per model, per workspace. Shows both aggregate totals and per-request averages.
Storage
Storage consumed by knowledge sources, artifacts, and cached data across all workspaces.
Dashboard Views
The dashboard offers multiple time granularities:
| View | Description |
|---|---|
| Daily | Hour-by-hour breakdown for the selected day |
| Weekly | Day-by-day breakdown for the selected week |
| Monthly | Day-by-day breakdown for the selected month |
Each view includes trend indicators showing whether usage is increasing or decreasing compared to the previous period.
Cost Breakdown
The cost breakdown section shows spending per:
- Provider -- how much you are spending with each model provider (OpenAI, Anthropic, Azure, etc.)
- Model -- cost per logical model, so you can see which models drive the most spending
- Workspace -- cost per workspace, so you can identify which teams consume the most resources
Spending Limits
Configure spending limits to prevent unexpected costs. Limits can be set at multiple levels.
Navigate to Spending Limits
In the billing dashboard, click the Spending Limits tab.
Set Organization-Level Limits
The organization-level limit is the overall spending cap for your entire organization.
- Monthly cap -- maximum spending per calendar month
- Action when reached -- choose to block new requests or send a notification to admins
Set Workspace-Level Limits
Click on a workspace to configure per-workspace limits:
- Monthly cap -- maximum spending for this workspace per month
- Daily cap -- maximum spending per day (optional, for tighter control)
- Action when reached -- block requests to this workspace or notify workspace admins
Limit enforcement
When a spending limit is reached and the action is set to block, requests to the affected scope are rejected with a rate limit error. Set limits with enough headroom for normal usage spikes to avoid disrupting production workloads.
Entitlement Tiers
Your organization's plan determines the available features, usage allowances, and support level.
| Feature | Starter | Professional | Enterprise |
|---|---|---|---|
| Workspaces | Up to 3 | Up to 20 | Unlimited |
| Users | Up to 10 | Up to 100 | Unlimited |
| API Calls / Month | 100,000 | 1,000,000 | Custom |
| Token Throughput | Standard | High | Custom |
| Audit Log Retention | 30 days | 90 days | 1 year+ |
| SSO / OIDC | -- | Included | Included |
| Priority Support | -- | -- | Included |
View your current plan and available upgrades in Admin -> Billing -> Plans.
Cost Optimization
MechaMental provides recommendations to help you reduce costs without sacrificing quality.
License Management
For self-hosted deployments, manage your license keys in Admin -> Billing -> License. License keys control:
- Which features are available on your instance
- The maximum number of users
- The expiration date
License renewal
License keys must be renewed before expiration. MechaMental sends automated reminders 30 days before expiry. Contact your account manager to renew or upgrade your license.