We use cookies to keep you signed in. Cookie policy
We use cookies
CalculatorAI uses cookies to keep you signed in and remember your preferences. Optional cookies help us understand how the site is used. Cookie policy
About $0.1564 per task on GPT-5.6 Terra: 8 model calls, each resending the conversation so far. At 1,000 tasks a month that is $156.40.
An AI sales development agent enriches a lead, checks the CRM, researches the company and drafts a personalised first email — we assume eight calls and about 1,500 tokens per tool result. On GPT-5.6 Terra, one task costs about $0.1564, and 1,000 tasks a month come to $156.40. The number that decides it is not the price per million tokens but how many calls one task takes — here 8 — because every call resends the whole conversation so far.
So the calls are not the same size. The first sends about 2,300 input tokens; the last, carrying everything before it, sends about 15,600 — 6.8× more. Per lead the cost is small; the budget question is volume and how much enrichment data you let into the conversation — a full company profile on every step multiplies quickly. The calculator below opens with this shape loaded: change the steps, the tool output and the volume to your own agent, and treat every figure here as an estimate from those assumptions, not a quote.
What One Agent Task Really Costs
Cost per task
One task · 5 calls to GPT-5.6 Terra
Cost per model call
$0.008640
averaged across 5 calls
Context growth
3.3×
1,800 tokens on the first call, 6,000 on the last
What drives one task
$0.0432At this volume
100 tasks · DayIf you ran this many tasks
100
$4.32
1,000
$43.20
10,000
$432.00
100,000
$4,320.00
What this figure assumes
Drop in a paystub, bank statement or screenshot — the AI reads it and fills these fields for you.
Income & Expense Tracker is where this stops being a one-off number: keep your real balances there and the projection updates itself.
Describe an invoice and the AI writes it. PDF without watermarks, free.
Same task shape on every row (2,000 system tokens cached, 300-token task, 400 tokens written and 1,500 returned by a tool per step). The last column doubles the steps: the input bill roughly quadruples because each call carries all the earlier ones.
| Model | Per task | Per month (1,000 tasks) | Per task at 16 steps |
|---|---|---|---|
| GPT-5.6 Terra | $0.1564 | $156.40 | $0.5524 |
| Claude Opus 5 | $0.3750 | $375.00 | $1.35 |
| GPT-5.6 Luna | $0.0156 | $15.64 | $0.0552 |
Use cases