Usage metrics

Widget Dashboard → Usage tab shows your consumption. At the top: Plan and Period (This Month / Last 30 Days / Custom) plus a Table/Chart view. This page explains what each metric means.

The Usage screen with sample data — **Usage, with sample data.** This month's cost at the top, then *used / remaining / total* for every measure. The daily table shows what each day spent, and agent credit is kept separate at the bottom.

Credit balance

When the credit model is active you see a single 💳 Credit Balance card: N credits left, Used this month: used / allowance (~$) and a 📈 At this rate ~N days left estimate.

💡

1 credit = $0.01. All your usage — chat, agent, voice, crawl — is drawn from one credit balance. So instead of "which row costs what", there's a single, understandable unit.

The What consumes credits? expander lists each operation's credit price. Fixed-price ones show N credits, metered ones pay as you go (up to N). The main credit-consuming operations:

Chat/assistant: chat message, reasoning, Q&A generation, smart content processing.
Knowledge base: web page crawl, KB embedding (per page), Q&A indexing (per page), storage (GB/month).
Agent: task planning/execution, tool use, web search, social-media reading, voice session.
Voice: voice reply (TTS), speech recognition (STT).
Memory: user memory, conversation summary, memory service, personal briefing, skill learning, quality patterns, security scan.

Resource metrics (label → meaning)

Separate from credits, resource metrics tracked against plan limits:

Metric	What it measures
Messages	Total messages in the period; counted against the plan's monthly message limit (chat + widget shared).
Bandwidth (MB)	Bandwidth consumed for web pages fetched through the proxy.
Pages Crawled	Total pages indexed via sitemap (per month).
Embedding Pages	Embedding page usage of ingested/searched data (1 page ≈ 750 tokens); counted against the plan embedding limit.
Storage	Total disk space used by the knowledge base + embeddings.

🔢

Token / Reasoning / Q-A rows are hidden when the credit model is active — because they're now folded into credits. (During the shadow period a Cost ($/TL) card and a separate 🤖 Agent Credits card may also appear.)

Hard ceiling & no surprise bills

Limits are a hard ceiling: when reached, new requests stop; no automatic overage charge. The widget shows your customer a graceful redirect, not an error; it resumes the moment you upgrade. To buy more: Subscription & Billing → Buy Extra Credits.

📖

Conceptual background (why the credit model): Credits & usage. Plan limits and plan-gating: Plans.

Was this page helpful? Send feedback

← Previous Reports Next → Subscription & Billing