Endpoint Stats

Endpoint

GET https://api.bve.me/admin/endpoint-stats
Authorization: Bearer admin_bve_YOUR_ADMIN_KEY

Returns request counts, error breakdowns, and latency aggregates grouped by the API endpoint path (e.g. /v1/chat/completions, /v1/embeddings). Data is sourced from the 1%-sampled request_logs_sampled table. Default sort order is request_count descending; use sort_by and sort_dir to change it.

Sampling caveat

request_logs_sampled stores roughly 1 in every 100 requests. All counts are a statistical sample, not exact totals. Multiply by ~100 for an order-of-magnitude estimate of actual traffic. For exact per-key totals, use Usage Statistics.

Authentication

Admin Bearer token required. See Admin API Overview for authentication details.

Query parameters

Parameter	Type	Required	Default	Description
key_id	string	No	—	Restrict stats to a single API key UUID
model	string	No	—	Restrict stats to a single model ID. Only rows where request_logs_sampled.model = ? are counted. Endpoints with no rows for that model are excluded. Combines with key_id.
since	string	No	—	Include only log entries at or after this ISO 8601 timestamp
until	string	No	—	Include only log entries at or before this ISO 8601 timestamp
limit	integer	No	20	Maximum number of endpoint rows to return (1–500)
sort_by	string	No	request_count	Column to sort by. One of: request_count, error_count, avg_latency_ms, max_latency_ms, p95_latency_ms
sort_dir	string	No	desc	Sort direction: asc or desc

All parameters are optional and combinable.

Response (200)

{
  "endpoints": [
    {
      "endpoint": "/v1/chat/completions",
      "request_count": 312,
      "error_count": 8,
      "client_error_count": 6,
      "server_error_count": 2,
      "avg_latency_ms": 1540,
      "max_latency_ms": 9200,
      "p50_latency_ms": 1100,
      "p95_latency_ms": 5800,
      "error_rate": 2.56
    },
    {
      "endpoint": "/v1/embeddings",
      "request_count": 87,
      "error_count": 0,
      "client_error_count": 0,
      "server_error_count": 0,
      "avg_latency_ms": 130,
      "max_latency_ms": 580,
      "p50_latency_ms": 120,
      "p95_latency_ms": 310,
      "error_rate": 0
    }
  ]
}

Response fields

Field	Type	Description
endpoint	string	API endpoint path as recorded in the request log (e.g. /v1/chat/completions)
request_count	integer	Number of sampled log entries for this endpoint (~1% of actual requests)
error_count	integer	Number of sampled requests that returned HTTP 400 or above
client_error_count	integer	Number of sampled requests that returned HTTP 4xx
server_error_count	integer	Number of sampled requests that returned HTTP 5xx
avg_latency_ms	number | null	Average end-to-end latency in milliseconds. null if no latency data was recorded.
max_latency_ms	number | null	Maximum end-to-end latency in milliseconds across all sampled requests for this endpoint. null if no latency data was recorded.
p50_latency_ms	number | null	Median (50th percentile) latency in milliseconds
p95_latency_ms	number | null	95th percentile latency in milliseconds — useful for tail-latency SLO alerting
error_rate	number	Error rate as a percentage: (error_count / request_count) × 100, rounded to 2 decimal places. 0 when request_count is 0.

cURL examples

All endpoints by request count

curl "https://api.bve.me/admin/endpoint-stats" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Top 5 endpoints in the last 7 days

curl "https://api.bve.me/admin/endpoint-stats?since=2026-05-19T00:00:00Z&limit=5" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Endpoint breakdown for a single key

curl "https://api.bve.me/admin/endpoint-stats?key_id=550e8400-e29b-41d4-a716-446655440000" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Endpoint breakdown for a specific model

# Which endpoints is gpt-4o being called through?
curl "https://api.bve.me/admin/endpoint-stats?model=gpt-4o" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Combined filter — model usage for a specific key

curl "https://api.bve.me/admin/endpoint-stats?key_id=550e8400-e29b-41d4-a716-446655440000&model=gpt-4o" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Sort by p95 latency (slowest endpoints first)

curl "https://api.bve.me/admin/endpoint-stats?sort_by=p95_latency_ms" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Sort by error count descending

curl "https://api.bve.me/admin/endpoint-stats?sort_by=error_count&limit=10" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Sort by avg latency ascending (fastest first)

curl "https://api.bve.me/admin/endpoint-stats?sort_by=avg_latency_ms&sort_dir=asc" \
  -H "Authorization: Bearer admin_bve_YOUR_ADMIN_KEY"

Pretty-print with jq

curl -s "https://api.bve.me/admin/endpoint-stats" \
  -H "Authorization: Bearer $ADMIN_KEY" \
  | jq '.endpoints[] | {endpoint, request_count, error_rate}'

TypeScript example

const res = await fetch("https://api.bve.me/admin/endpoint-stats?limit=10", {
  headers: { Authorization: `Bearer ${adminKey}` },
});

const { endpoints } = await res.json();

for (const ep of endpoints) {
  console.log(`${ep.endpoint}: ${ep.request_count} sampled requests, p95=${ep.p95_latency_ms}ms`);
}

Common errors

Status	Code	Cause
400	validation_error	since or until is not a parseable ISO 8601 timestamp
400	validation_error	sort_by is not one of the accepted column names
400	validation_error	sort_dir is not asc or desc
401	missing_api_key	No Authorization header
401	invalid_api_key	Admin key does not match the configured ADMIN_API_KEY secret

Use cases

Find the slowest endpoint by p95 latency:

curl -s "https://api.bve.me/admin/endpoint-stats?sort_by=p95_latency_ms&limit=1" \
  -H "Authorization: Bearer $ADMIN_KEY"

Find endpoints with the most errors:

curl -s "https://api.bve.me/admin/endpoint-stats?sort_by=error_count" \
  -H "Authorization: Bearer $ADMIN_KEY" \
  | jq '.endpoints[] | select(.error_rate > 5)'

Find which endpoints a specific model is called through:

curl -s "https://api.bve.me/admin/endpoint-stats?model=gpt-4o" \
  -H "Authorization: Bearer $ADMIN_KEY" | jq '.endpoints[] | {endpoint, request_count}'

Compare endpoint usage for a specific key:

curl -s "https://api.bve.me/admin/endpoint-stats?key_id=<uuid>" \
  -H "Authorization: Bearer $ADMIN_KEY" | jq '.'

Next steps

Key Stats Top API keys by request count with token totals and latency percentiles

Model Stats Per-model aggregate request counts, token sums, and latency

Request Logs Browse individual sampled log entries with per-request detail

Admin API: Overview All admin endpoints in one table