Works locally, fails in prod (LLM)

What engineers usually see

  • •LLM requests succeed in development
  • •Same requests fail or timeout in production
  • •Difficult to reproduce production conditions
  • •No clear difference in request parameters

Why this is hard to debug

Production failures that don't reproduce locally are notoriously hard to debug. Standard logs don't capture environment differences. Receipts provide identical debugging capabilities in dev and prod.

Minimal repro

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_OPENAI_KEY',
  baseURL: 'https://aibadgr.com/v1'
});

const response = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{role: 'user', content: 'test'}]
});

console.log(response.id);

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

  • Dev vs prod execution comparison
  • Network latency differences
  • Provider routing differences
  • Rate limit state in production
  • Infrastructure-specific delays

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.