Infrastructure

Tracing

BitRouter Cloud traces every request into a hosted Activity view — spend, token, and latency KPIs plus a per-request log — with nothing to operate. Deep OTel span waterfalls link out to your own collector.

The open-source OpenTelemetry export runs on your own backend. BitRouter Cloud gives you the hosted alternative: every /v1 request is traced into an Activity view server-side — no collector, no warehouse, nothing to run. Content (prompts and responses) is never stored.

The Activity dashboard

Sign in to cloud.bitrouter.ai and open Activity. It opens on three KPI cards over a window you pick — 1 day, 1 week, 1 month, or all time:

KPIWhat it measures
SpendTotal USD charged over the window
RequestsNumber of requests over the window
TokensPrompt + completion tokens over the window

Every figure is scoped to the active workspace (namespace), so a dashboard always reflects the workspace you're signed into.

The request log

Below the KPIs, the request log lists every /v1 request, newest first. Each row is a per-request trace record:

ColumnDetail
TimeWhen the request landed
ModelThe model id served, with a stream marker for streamed calls
ProviderThe upstream provider that served it
TokensPrompt + completion total
CostFinal charge in USD
LatencyEnd-to-end latency
SourceFunding source (credit balance, BYOK, MPP session)
StatusSucceeded, error, denied, cancelled

Each record also carries the routing profile used (balanced, cost, latency, throughput) and the gated capabilities exercised (e.g. structured_outputs) — so a request that failed over or hit a budget is legible without leaving the dashboard.

Receipts, not bodies. Cloud stores the request record — model, provider, tokens, cost, latency, status, routing profile — never the prompt or response content.

Usage attribution & the API

Everything in the dashboard is also available over the management API, scoped per workspace and gated by the usage:read scope:

  • Aggregate usage — spend, token counts, request count, and a per-capability breakdown over a [from, to) window.
  • Request history — the paginated request log, including routing profile and capabilities used.

These are the same bitrouter cloud usage and bitrouter cloud requests commands you run from the CLI. See the API Reference for the usage and requests endpoints and their fields.

Deep traces

Cloud stores per-request receipts, not OpenTelemetry span waterfalls. When you need the full span tree — the ingress span, the routing decision, and a CLIENT span per upstream attempt — that lives in your own OTLP collector. Wire it up once with the open-source OpenTelemetry export and the Activity view links out to it.

Next steps

How is this guide?

On this page