Latency Budgets
Latency budgets let organizations define per-model targets for end-to-end request latency and time-to-first-token (TTFT). The reporting endpoint compares actual percentiles fromllm_usage_events against budgets and reports whether each percentile is within budget, exceeded, or missing data.
All latency budget endpoints require the caller to be an organization owner or admin.
Base URL
Endpoints
Budget fields
Use
* as the model_id to define a global default budget.
List budgets
Response
Set a budget
Response
Delete a budget
204 No Content on success.
Latency report
window_hours defaults to 24 and is capped at 168 (7 days).
Response
Status values
Error codes
Related pages
- Admin Analytics — request volume and token usage reports
- Fallback Retry Policy — configure retries for slow or failing providers