Skip to content
Router One

LLM observability: one trace per request

Router One records model-call usage in Dashboard → Logs. Filter by model and time range, then open a row for its request ID, tokens, recorded latency, status and any sanitized error. Check the stream's final event separately from its HTTP status, and use the recorded settlement to confirm its charge. Support can correlate the request ID with internal routing attempts.

Get your API key

What can you inspect in a request log?

SignalRouter One traceHow to interpret it
Request ID & modelOpen the row to copy requestId and inspect the recorded modelMatch the ID with the same call in your application's logs
Input / output tokensRecorded input/output counts and cache-read tokens when availableUsage does not prove the client received a complete answer
Cost per requestRecorded totalCost after settlement; pending means the amount is unknownThe settled total already includes applicable pricing multipliers
LatencyRecorded request latency; a missing value displays as a dashMeasure time to first visible token separately in the client
Routing investigationA request ID for support correlationProvider names and the attempt chain are not displayed in customer Logs
Status code & errorsStatus code and sanitized error text when availableHTTP 200 alone cannot prove a streamed answer completed
Spend ceilingPer-key maxSpend stops a runaway loopSet a separate loop limit in your application too

Where to look

Dashboard -> Logs

Filter by model and date range, then open the matching row for its request ID, usage, status and settlement details. A record may not appear immediately while pricing is pending. Keep workload and API-key labels with request IDs in your own application logs.

Dashboard -> Usage

Review request, token and spend trends plus per-model and capability breakdowns. The current Usage screen does not display a per-API-key breakdown. Inspect the individual Logs row for the recorded charge and any supplied discount details.

Budgets & rate limits

Each API key carries its own maxSpend plus rateLimit and tokenLimitTpm. A runaway loop hits its own ceiling and stops instead of draining the whole balance — spend control without a governance suite.

Example: a request awaiting settlement

Synthetic excerpt using customer Logs fields. Values are illustrative, not a production trace or price quote. If a row is marked pending, its final cost is unknown; records awaiting pricing may temporarily be absent from the list.

trace.json
{
  "requestId": "demo_req_7f3a",
  "model": "example-chat-model",
  "inputTokens": 512,
  "outputTokens": 200,
  "latencyMs": 1180,
  "statusCode": 200,
  "totalCost": null,
  "billingPricing": {
    "status": "pending"
  }
}

Request-data handling

The customer trace contains request metadata for debugging and billing review. Router One does not retain prompt or model-response bodies from direct API calls. It records request metadata for billing, usage tracking, and troubleshooting. Playground saves conversation history so users can revisit and continue their chats.

Read the data retention policy

FAQ

Does HTTP 200 mean my streamed answer succeeded?

No. HTTP 200 can indicate that the stream opened before generation failed or became incomplete. For Chat Completions, inspect finish_reason and any stream error; stop, length and tool_calls mean different things. For Responses, examine response.completed, response.failed or response.incomplete. A closed connection or a dashboard success badge alone is insufficient.

Does Pending settlement mean this request was free?

No. Pending settlement means the final charge is unknown. The UI does not substitute $0 or undiscounted token subtotals. Check the row again later; the settled total already includes applicable discounts. Any displayed default or model-specific discount, plan multiplier and effective multiplier explain that total rather than being another discount to apply.

What evidence should I collect for a slow or failed request?

Keep the request ID, timestamp with timezone, endpoint, exact model ID, SDK version, timeout settings, HTTP status and final error or finish reason. Record when the first visible token arrived and whether you cancelled. Compare similar models, endpoints and prompt sizes across multiple calls; a single duration cannot identify the cause. Remove API keys and sensitive input/output before sharing.

What exactly is in a trace?

Customer Logs shows the recorded model, request ID, input/output tokens, available cache-read tokens, settled cost or a pending label, recorded latency, status code and any sanitized error. Pricing details appear when supplied. Provider names and intermediate attempt chains are not displayed there.

Does Router One store my prompts and responses?

Router One does not retain prompt or model-response bodies from direct API calls. It records request metadata for billing, usage tracking, and troubleshooting. Playground saves conversation history so users can revisit and continue their chats.

How do I stop a runaway loop from draining my balance?

Give the API key a maxSpend, plus rateLimit and tokenLimitTpm. When a loop hits the key's spend ceiling or rate limit, requests on that key stop instead of consuming the whole wallet. Budgets are per key, not per project.

Is this an enterprise audit or compliance platform?

No. This is request-level observability and spend control for developers and small teams. It is not an enterprise audit, compliance, or RBAC system. There is no organization/role structure — limits and budgets attach to API keys.

What does the trace show when a provider fails?

Customer Logs records the resulting model-call usage, status and any sanitized error. It does not show provider names or the fallback chain. Support can use the request ID to investigate intermediate attempts in operational logs; retain the client error and terminal event too.

Related

See every request, control every dollar

Get your API key