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/{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 . Payloads See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

omni-usage-logs