{% extends "base.html" %} {% block content %}

Generations & Cost

LLM cost tracing — token usage, spend over time, and the context behind every generation.

Cost over time

daily LLM spend (USD)

Token split

input vs output

Cost by model

total spend per model

Calls over time

generations per day

Per-model breakdown

Recent generations

The exact prompt/context and the response, with cost. Click a row to expand.

{% endblock %} {% block scripts %} {% endblock %}