[OBSERVABILITY]

See every AI request your app makes.

Inspect prompts, trace multi-turn conversations, and catch issues before they hit production. Full request/response logging with zero code changes. Need observability without the proxy hop? Trace mode sends requests directly to your provider and streams metadata async.

[What it does]

Grepture logs every LLM request and response flowing through your app. You get a real-time traffic log showing prompts, completions, token counts, latency, and status codes — across every provider and model. In trace mode, requests bypass the proxy entirely and go straight to the provider. The SDK captures metadata (tokens, model, latency) and sends it async — zero latency overhead, full dashboard visibility.

[How it works]

Point your SDK at Grepture (one config line). Every request is captured, indexed, and searchable in the dashboard. Filter by model, endpoint, status, or time range. Trace full conversation threads across multiple requests. For latency-sensitive workloads, set mode: "trace" — requests go directly to the provider while trace data flows to your dashboard in the background.

app.grepture.com/traffic-log
TimeMethodURLDuration
2s agoPOST/v1/chat/completions1.2s
5s agoPOST/v1/embeddings84ms
12s agoPOST/v1/chat/completions2.4s
18s agoPOST/v1/messages12ms
31s agoPOST/v1/chat/completions890ms
45s agoPOST/v1/chat/completions3.1s
[Key features]
  • +Real-time traffic log with prompt/response inspection
  • +Multi-turn conversation tracing across requests
  • +Filter by model, provider, endpoint, or status code
  • +Token usage and latency metrics per request
  • +Full request/response body search
  • +Works with OpenAI, Anthropic, Google AI, and 10+ providers
  • +Trace mode — observe without the proxy hop, zero latency overhead

See your first trace in under 60 seconds

npm install @grepture/sdk — wrap your client — done.

Free for up to 1,000 requests/month · No credit card required

Get Started Free