Token explosion in LLM

What engineers usually see

  • •Request uses far more tokens than expected
  • •Input or output tokens much larger than anticipated
  • •Cannot identify what caused the token spike
  • •Costs scale unexpectedly

Why this is hard to debug

Token counting is opaque and model-specific. You can't predict token usage from input text. Receipts show actual vs expected tokens and highlight anomalies.

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: 'Explain quantum computing'}]
});

console.log('Tokens used:', response.usage);

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

  • Input tokens (prompt)
  • Output tokens (completion)
  • Total tokens
  • Cost per token tier
  • Token usage trends

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.