Costs

wireConnecting to Teglo, loading live spend from get-cost-summary…
The AI's whole billreal
all-time
This monthreal
vs $50 cap
Cost to serve a callreal
true all-in, per call
Time it savedmodelled
vs a person, 8 min/call x $30/hr

Your AI assistant spends more on its brain than its voice.

real · by action
Brain · · memory sync + LLM + analysis Voice · · Vapi minutes + speech in/out from the Vapi end-of-call breakdown
Where the money goes by model
donut
all-time
One model carries the bill.
Choose a variant
locks for this client
UPSERT canonical_section_variant_locks · client-scoped
Cost vs the revenue it rides on real
donut
of monthly revenue
AI cost
Platform MRR · all Teglo
·
of monthly revenue · the AI is a rounding error
Against the whole platform's revenue, the AI is a rounding error.
Choose a variant
locks for this client
UPSERT canonical_section_variant_locks · client-scoped

Cost to serve, per client real · from calls

Per-call cost attributed to each client from the Vapi end-of-call breakdown. Unattributed = calls on a Vapi number not yet mapped in call routing.

Cost by the job the AI is doing real

Names from vertical_personas (voice personas). Untagged is biggest until the AI stamps the job on each event. Job x channel is the dream cut, once a channel tag exists.

Budget spend real

used this month
·cap $50
Budget + alert thresholds live in Settings (client_financial_config). Alerts at 80% and 100%. Never a kill-switch, a live call is never cut.

Every cost event real

WhenWhatRan onModelPersonaCost
loading…

Cost to serve, per call real

WhenClientChannelTop modelPartsCost
loading…

Platform overhead actual · monthly

infraFixed monthly platform costs the per-call cost rides on. Dev tooling is shown separately and is not cost-to-serve.
SourceBasisAmount
loading…

Full cost picture · ORA-internal est / not costed

SourceLevelPeriodPrice
loading…