Skip to content

effGen

Playground Connecting…
Total Requests
Model-call Errors
Avg Latency
Cost (session)
Tokens Used

SLO Burn Rates

p99 latency
error rate
availability

Request Latency (recent)

By Model

Calls, error rate, latency, tokens and cost per model and provider
Outcome Tokens (in/out)
Loading…

HTTP Responses by Status

Loading…

Responses by Route

Requests, failures and the share of each route's traffic that failed. Anything outside the recorded route list — the dashboard's own polling, and any unrouted request — is counted as other, not as user traffic.

HTTP requests, errors and error rate per route and method
Method By class
Loading…

Recent Agent Runs

The most recent agent runs
Time Model Tokens (in/out) Cost Duration Status
Loading…

History

Loading stored runs…

Stored runs, newest first
When Model Task Cost Duration Status
Loading…

Saved Sessions

Saved chat sessions
Session Messages Model Cost Updated
Loading…

Live Span Stream

0 spans

Run Timeline

Spans grouped by run — bars positioned by start offset, width by duration.

No runs recorded yet.

Agent Topology

Loading recorded executions…

No multi-agent activity recorded yet.

Model Catalog

Loading catalog…

Model catalog: context window, output limit, price and capabilities
Provider Model ID Context Max Out $/1M in $/1M out Tools Vision Free
Loading…

Prometheus Metrics (raw)

Raw Prometheus metric samples
MetricValue
Loading…