LLM request hangs in production

What engineers usually see

  • •Request works fine locally but hangs in production
  • •No error, just infinite wait
  • •Cannot reproduce locally with same parameters
  • •User-facing features become unresponsive

Why this is hard to debug

Production hangs are environment-specific. Without prod-like observability in development, you can't debug the issue. Receipts work the same in all environments and provide consistent diagnostics.

Minimal repro

curl https://aibadgr.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_OPENAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "test"}]
  }'

This request routes through AI Badgr and returns a stable request ID that links to an execution record.

Note: AI Badgr is OpenAI-compatible and works as a drop-in proxy. No SDK changes required — only the base_url changes.

What a per-request execution record makes visible

  • Environment-specific timing
  • Network path in production
  • Provider routing differences
  • Queue wait times
  • Infrastructure bottlenecks

Run 1 request → get receipt

Change your base URL to https://aibadgr.com/v1 and run your request.

The response includes an X-Badgr-Request-Id header that links to a receipt showing latency, retries, tokens, cost, and failure stage for that specific execution.

Get API Key

Not the engineer?
Share this page with your dev and ask them to run one request through AI Badgr. That's all that's needed to get the receipt.

This kind of thing only makes sense when you can actually see what happened to a single request from start to finish, instead of trying to piece it together from scattered logs.