Account & Billing
Usage & analytics
The Analytics tab reads from your billing data, what you see is exactly what you're billed.
The dashboard's Analytics page aggregates your organization's usage by day and model over a 7, 30, or 90-day window. The numbers come from the billing pipeline itself, not a separate metrics system, so the spend you see here reconciles with your payment history and invoices by construction. Playground traffic is included; it's billed like any API call.
The four tabs
| Tab | What it shows |
|---|---|
| Usage | Tokens per day, stacked by model, with totals for input, output, and cached input tokens (each as a share of all tokens) |
| Cost | Spend per day and per model, the same rated figures your invoices are built from |
| Caching | Cached vs. uncached input tokens and your effective hit rate, the feedback loop for prompt-caching work |
| Activity | The daily aggregates as a table, newest day first, day × model, tokens, and spend |
Cost figures are shown at full precision rather than rounded to cents, at fractions of a dollar per million tokens, the digits past the cent are where your actual spend lives.
Why there are no per-request logs
Analytics are deliberately day × model aggregates: the platform does not keep a browsable log of individual requests, and nothing about your prompts feeds these numbers. Whether the network retains prompts and completions at all is your organization's choice: switch Store prompts off on the API Keys page and they are not persisted, full privacy (see the terms of service for the data-handling details). For request-level debugging, work from your side of the wire:
- Log the
request_idfrom error responses and theidfrom successful ones, support can trace a specific request from those (see error handling). - Record the
usageobject your application receives per response, it is the same accounting that rolls up into these aggregates.
What's worth watching
- Cached-input share (Caching tab): if it's low for an agentic or chat workload, restructure prompts per the prompt caching guide, it's usually the cheapest optimization available.
- Cost by model (Cost tab): a surprising leader often means a workload is running on a bigger model than it needs, see Choosing a model.
- Output-token share (Usage tab): reasoning models bill their thinking as output tokens, so a jump here after adopting them is expected, tune with
reasoning.effort.
Every member of your organization can view Analytics, it has no billing controls, so it is safe to share broadly as the team's common picture of usage and spend.