Usage and analytics
Flux measures four things: triggers, tokens, sessions and cost. The analytics dashboard breaks each one down by where it came from.
The four numbers
| Metric | Counts | Driven by |
|---|---|---|
| Triggers | Times a workflow started | Messages received, API calls, interval firings, spreadsheet rows |
| Tokens | Input and output consumed by AI nodes | Prompt length, memory depth, tool descriptions, answer length |
| Sessions | Distinct runs, including multi-message conversations | How many conversations, not how many messages |
| Cost | What the above adds up to | Provider rates for each metric |
The dashboard shows Today and This Month.
The analytics dashboard with four summary tiles for triggers, tokens, cost and sessions, and charts for trigger distribution and cost breakdown below
Screenshot to be addedThe five views
| Tab | Shows |
|---|---|
| Overview | Trigger distribution, cost distribution and token usage together |
| Triggers | Trigger types, comparison between them, and where volume comes from |
| AI Models | Token distribution, usage against cost, and the cost breakdown per model |
| Messaging | Usage per channel — WhatsApp, Viber, Telegram, Facebook, Instagram |
| Speech | Speech-to-text and text-to-speech consumption |
Where usage comes from
Every provider is counted separately, with its own unit:
| Provider | Measured in |
|---|---|
| Flux UI, Flux API, Flux Interval | Triggers |
| WhatsApp, Viber, Telegram, Facebook, Instagram | Triggers |
| Cognify inbound chat | Triggers |
| GPT, Gemini | Tokens |
| Speech-to-text | Seconds |
| Text-to-speech | Characters |
What actually drives cost
It is rarely the number of nodes. In practice:
- Conversation length. With memory attached, the whole history is sent on every message — so a twenty-message conversation costs far more than twenty separate one-message ones.
- Tool count. Every tool's description is sent on every call. Six tools cost more per message than two.
- Interval frequency. A one-minute interval is 1,440 triggers a day, plus whatever each run consumes downstream.
- Prompt length. A long system prompt is paid for on every single message.
If cost is higher than expected, check the AI Models tab for usage
against cost, then the Triggers tab for what is firing. An interval you
set to test and forgot is the most common surprise.
Reducing it
- Lengthen intervals. Ask whether every fifteen minutes is really needed.
- Trim the system prompt. It is paid for on every message.
- Remove unused tools. Each one is described on every call.
- Filter earlier. A Decision node before the AI node stops you paying for messages that never needed a model.
- Compare models. Run the same prompt on GPT and Gemini and read the cost side by side.
Usage and billing
Usage on Flux's built-in keys draws down your project's credits wallet. Usage on your own credentials is billed by the provider directly and does not touch the wallet. See Billing and credits.