Why did this request cost so much?

What engineers usually see

  • •Single request costs unexpectedly high
  • •Cannot identify what drove the cost
  • •May be due to long output, retries, or model choice
  • •No breakdown of cost components

Why this is hard to debug

High-cost requests aren't flagged in standard logs. You have to manually calculate cost from tokens and model pricing. Receipts automatically highlight expensive requests and explain why.

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',  // Expensive model
  messages: [{role: 'user', content: 'Write a detailed essay'}],
  max_tokens: 4000
});

// Check receipt for cost breakdown

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

  • Cost breakdown (input, output, model)
  • Token usage vs limits
  • Comparison to average request cost
  • Whether cost was due to retries
  • Optimization suggestions

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.