Skip to main content
The Usage dashboard tracks your API consumption, helping you monitor requests, tokens, and costs.

Accessing Usage

1

Open Gloo AI Studio

Log in to Gloo AI Studio.
2

Choose your organization

Select your organization from the organization switcher.
3

Open Usage

Click Usage in the Build section of the main navigation.

Available Metrics

Shorter prompts and responses consume fewer tokens and cost less. Review usage regularly to spot optimization opportunities.

Filtering Usage Data

When this is useful: Track usage per application, environment (development vs. production), or team to identify optimization opportunities.

API Usage by Capability

The Usage dashboard also breaks usage down by capability (Models, Chat, etc.), showing which features drive your consumption.

Understanding Your API Usage

Request Counts

Each call to the Gloo AI API counts as one request, regardless of the size of the input or output. Requests are tracked by:
  • Endpoint called (e.g., Chat, Recommendations)
  • Timestamp
  • API key used
  • Response status (success or error)
Use request counts to understand your application’s call patterns and identify peak usage times.

Token Metrics

Tokens are the units of text AI models process:
  • Input Tokens: The number of tokens in your input to the API (your request, context, and system messages)
  • Output Tokens: The number of tokens in the API’s response (the generated text)
  • Cache Tokens: Input tokens read from or written to a prompt cache, billed at cache rates
Pricing is typically based on tokens, and output tokens often cost more than input tokens.
Different models have different token costs. See the Models page in Studio, or GET /platform/v2/models, for current rates.

Cost Tracking

The Usage dashboard shows costs from actual API usage:
  • Daily costs: Total spend per day
  • Weekly totals: Spend over the past week
  • Monthly totals: Cumulative spend for the billing period
How those costs are tracked depends on how your organization pays:

Rate Limits vs. Spend Limits

Rate limits control request speed. Spend limits control spending. See Billing & Plans for details.

Frequently Asked Questions

Usage data updates in near real time, typically within a few minutes of each call. Some aggregated metrics (like daily totals) may take up to an hour to fully update.
Self-serve accounts can view usage in the dashboard. Enterprise accounts can export detailed reports; contact your account manager for options.
The dashboard keeps your historical API usage. Enterprise accounts can ask their account manager about extended history and exports.

Next steps

To bring these numbers down and see which feature drives them, read Controlling Cost.

Billing & Plans

Products, tiers, and spend limits.

Prepaid Credits

Add credits and set up auto-refill.

Generate API Keys

Create keys for your integrations.