Access detailed call logs and usage analytics. Filter by provider, model, time range, status, and cost. Export logs and aggregate token usage across all connections.

<! generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten Overview Access detailed call logs and usage analytics. Filter by provider, model, time range, status, and cost. Export logs and aggregate token usage across all connections. Authentication All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE API KEY=false for local development. Endpoints GET /api/usage/analytics Get usage analytics GET /api/usage/call logs Get call logs GET /api/usage/call logs/filters Get call log filter options Distinct providers, models, accounts and API keys seen in call logs, plus every configured API key (id and name only). Feeds the Logs tab filter dropdowns. GET /api/usage/call logs/{id} Get a specific call log GET /api/usage/{connectionId} Get usage for a specific connection GET /api/usage/history Get usage history GET /api/usage/logs Get usage logs GET /api/usage/proxy logs Get proxy logs GET /api/usage/request logs Get request logs GET /api/usage/budget Get usage budget status Returns current budget limits and consumption. POST /api/usage/budget Configure usage budget Set or update budget limits for usage tracking. GET /api/usage/cache health Get prompt cache health summary Summarizes the write/read cache ratio from call logs for a time window: distribution (p50/p90/p99/max of cache write tokens), warm/cold/rewrite/uncached call counts, the "heavy write" outlier share (10x the window median, floored at 1024 tokens — Anthropic's cache creation minimum), and a per model breakdown. Only successful ( status = 200 ) calls with a non null cache column are counted. GET /api/usage/model latency stats Get per model/provider latency statistics Aggregates usage history rows into per (provider, model) latency stats (avg/p50/p95/p99, std dev, TTFT, tokens/sec) over a rolling window. Falls back from successful only to all sample rows when the successful count is below minSamples . GET /api/usage/budget/bulk GET usage › budget › bulk GET /api/usage/codex reset credit GET usage › codex reset credit POST /api/usage/codex reset credit POST usage › codex reset credit GET /api/usage/combo forecast GET usage › combo forecast GET /api/usage/combo health GET usage › combo health GET /api/usage/combo health autopilot GET usage › combo health autopilot GET /api/usage/combo health dashboard GET usage › combo health dashboard GET /api/usage/combo scoring inspector GET usage › combo scoring inspector GET /api/usage/combo trace/{id} GET usage › combo trace › <id GET /api/usage/om usage GET usage › om usage GET /api/usage/provider limits GET usage › provider limits POST /api/usage/provider limits POST usage › provider limits GET /api/usage/provider window costs GET usage › provider window costs GET /api/usage/quota GET usage › quota GET /api/usage/requests by provider date GET usage › requests by provider date GET /api/usage/route explain/{id} GET usage › route explain › <id GET /api/usage/token limits GET usage › token limits POST /api/usage/token limits POST usage › token limits Save a per key token limit. A key holds one limit per scope and reset interval, so daily, weekly and monthly limits for the same scope coexist. Without id , a new limit is added (or the key's limit for the same scope and interval is updated); with id , that limit is updated. DELETE /api/usage/token limits DELETE usage › token limits GET /api/usage/utilization GET usage › utilization Payloads See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

omni-usage-logs