Skip to main content
AI usage & cost

Ten cases. About a dollar.

This is a constructed scenario, not a single account. We assembled a mix of cases designed to simulate roughly a month of usage for a large customer — reports arriving across all four intake modalities, with a deliberate spread of light and heavy back-and-forth, plus investigator AI-helper sessions of varying depth on the cases that warranted them. Every figure is modeled on the actual prompt paths in the app, priced on Claude Sonnet 4.5.

01
10
cases in the scenario
02
268.8K
tokens up (input)
03
18.9K
tokens down (output)
04
$1.09
est. monthly cost

That works out to roughly $0.11 per case.

Rate card & assumptions

What each AI job costs

Per-unit rates derived from the live intake and investigator prompt paths.

ModelClaude Sonnet 4.5 — $3 / M in · $15 / M out
Auto title (every case)~0.7K↑ / 0.03K↓
Chat intake — full history re-sent each turnlight 8K↑/0.6K↓ · heavy 30K↑/1.8K↓
Webform completeness reviewlight 0.7K↑/0.2K↓ · heavy 2.1K↑/0.6K↓
Phone / Email intake — human-handled0 AI tokens
AI helper — agentic, tool-callinglight 12K↑/1K↓ · heavy 45K↑/3K↓

“Light / heavy” reflects the depth of back-and-forth. Chat intake cost scales fastest because the whole conversation is re-sent on every turn; the case AI helper scales with how many investigator questions are asked and how often it pulls the full case.

The month, case by case

Ten reports, a mix of depths

CaseModalityIntake loadAI helperTokens ↑Tokens ↓Est. cost
CH-1042ChatHeavy~14 turnsHeavy~7 sends, full pull75,7004,830$0.30
CH-1043ChatLight~5 turnsLight~3 sends20,7001,630$0.09
CH-1044WebformHeavy3 passesHeavy~7 sends, full pull47,8003,630$0.20
CH-1045WebformLight1 check1,400230$0.01
CH-1046PhoneHumanno AI intakeLight~3 sends12,7001,030$0.05
CH-1047PhoneHumanno AI intake70030$0.003
CH-1048EmailHumanno AI intakeHeavy~7 sends, full pull45,7003,030$0.18
CH-1049ChatHeavy~14 turnsLight~3 sends42,7002,830$0.17
CH-1050ChatLight~5 turns8,700630$0.04
CH-1051EmailHumanno AI intakeLight~3 sends12,7001,030$0.05
Month total — 10 cases268,80018,900$1.09

Where the money goes

Two patterns dominate spend: heavy chat intakes (full conversation re-sent each turn) and heavy AI-helper investigations (the agent re-pulls the full case on every question). Phone and email reports cost essentially nothing until an investigator opens the helper.

Illustrative model. Actual per-message token counts are captured in the platform's AI usage records.