HQL is currently available to selected workspaces. If you don’t see the HQL page in your dashboard, click “Request Access” from the HQL screen or contact support.
What you can query
- request_created_at: timestamp of the request
- request_model: model name used (e.g.
gpt-4o
) - status: HTTP status code
- user_id: your application user identifier (if provided)
- cost / provider_total_cost: cost metrics
- prompt_tokens, completion_tokens, total_tokens: token usage
- properties: custom properties map (e.g.
properties['Helicone-Session-Id']
)
Examples
Top costly requests (last 7 days)
Error rate (last 24 hours)
Active users by day (last 14 days)
Session analysis using custom properties
Cost by model (last 30 days)
How to use HQL
In the Dashboard
- Go to
HQL
in the sidebar - Browse tables and columns in the left panel
- Write your SQL in the editor
- Press Cmd/Ctrl+Enter to run; Cmd/Ctrl+S to save as a query
Via API
Interactive API documentation is available at: https://api.helicone.ai/docs/#/HeliconeSqlAPI Limits
- Query limit: 300,000 rows maximum per query
- Rate limits: 100 queries/min, 10 CSV downloads/min