Usage and invoices
Where to see your FluxRouter usage and spend, how to read the cost of a single request, and where to find invoices.
FluxRouter shows the cost of each request on the response, your running usage and spend in the dashboard, and invoices on the billing page.
Where do I see my usage and spend?
Open /home/usage. It opens on this month so far and shows usage and spend for the period you pick, broken down by model, lab and key, with a CSV export, and your headroom against any spend caps. You can narrow it to one key. How many calls each model answered this week, and which keys made them, is at /home/activity.
Your plan, payment method, balance and billing history are at /home/billing.
How do I see what a single request cost?
A non-streaming response carries an X-Flux-Cost-Usd header with the cost of that request in USD:
curl -i https://api.fluxrouter.ai/v1/chat/completions \
-H "Authorization: Bearer $FLUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-auto",
"messages": [{ "role": "user", "content": "ping" }]
}'
# Response headers include:
# X-Flux-Model: ...
# X-Flux-Cost-Usd: ...
On a streamed response the cost is only known after the headers have gone, so it arrives in the final usage block of the stream and in your dashboard, not in the header.
Alongside the cost you get X-Flux-Model (the model that answered) and X-Flux-Request-Id (the id to quote to support). See Receipts.
Where are my invoices?
Invoices and payment history are at /home/billing, where you can view and download them and update your payment method.
- Free is never charged, so there is nothing to invoice. See The Free plan.
- Pay As You Go bills your metered usage each period, with no monthly fee.
- Builder (and Scale, for accounts already on it) bills the plan fee, plus any usage above the included credit. See Plans.
How is the cost on my invoice calculated?
Each request is metered by tokens at the rate of the alias it used, and each ability call at its per-use rate, summed over the period. flux-auto bills at the Standard rate, or the Fast rate when it sends your request to the Fast lane and a Fast model answers. Never more than Standard. See How billing works.