Know what every
conversation costs.
Vectrant logs every LLM call — model, tokens in, tokens out, cost, pipeline, and conversation ID. The Billing tab in the Intelligence Hub shows cost per conversation, cost per pipeline, daily/weekly/monthly totals, and model breakdowns. No surprise invoices. No black-box billing. You see exactly what the AI is spending and where.
Token-level visibility, dollar-level clarity.
Every LLM call is logged with full metadata. Roll up by conversation, pipeline, model, or time period. Export to CSV for your finance team.
Per-conversation cost
See the exact dollar cost of every conversation — broken down by each LLM call (orchestrator routing, knowledge retrieval, response generation). Compare cost per resolved vs. unresolved conversation.
Pipeline breakdown
Which pipelines are the most expensive? Knowledge base queries, product lookups, troubleshooting sessions, and custom pipelines each show their share of total cost.
Model selection audit
Track which AI model handles each call — Haiku for fast routing, Opus for executive tasks. See cost differences and optimize model selection for your usage patterns.
LLM Metering, transparent from day one.
30-minute walkthrough on your real catalog. No slideware, no demo data.