LLM cost attribution

What engineers usually see

  • Cannot attribute AI costs to specific customers or features
  • Shared API key makes cost tracking impossible
  • No per-tenant or per-feature cost visibility
  • Difficult to bill customers or allocate budgets

Why this is hard to debug

Provider billing is per API key, not per tenant or feature. You need custom tagging and aggregation to track costs. Receipts support cost attribution via request metadata.

Minimal repro

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_OPENAI_KEY",
    base_url="https://aibadgr.com/v1"
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "test"}],
    # Add metadata for attribution
    extra_headers={"X-Customer-ID": "customer-123"}
)

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 per request with metadata
  • Customer/tenant attribution
  • Feature-level cost breakdown
  • Cumulative spend by segment
  • Cost allocation reports

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.

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.