Cadence and cost

This page explains why Agency runs daily, Growth runs each prompt three times a week, and Starter runs weekly — why each tier gets the run budget it does, why we won't sell more runs than each tier currently includes, and why the tier limits look the way they do.

If you've ever wondered why a tool that looks simple has the pricing it does, this is the page.

The cost per prompt

Every time we run one of your prompts, we hit 6 AI engines in parallel:

ChatGPT (OpenAI API)
Claude (Anthropic API)
Gemini (Google API)
Perplexity (Perplexity API)
Microsoft Copilot (Bing via SerpAPI + GPT-4o-mini synthesis)
Google AI Overviews (SerpAPI)

Each engine charges per request. The exact pricing varies by provider and model, and providers update their rates. We deliberately route to cost-efficient models (gpt-4o-mini and claude-haiku) on the synthesis steps so the per-engine spend stays low without losing answer quality.

Multiply by 6 engines, add the parsing, classification, and storage overhead, and a prompt-run currently costs us $0.25–$0.30 in API spend. That range is the foundation of every tier limit.

That's not a guess — it's measured from production telemetry (updated July 2026, after we found Gemini's "thinking" tokens weren't being counted; the earlier ~$0.15 and ~$0.22 figures predate that fix). It moves as providers tweak pricing — Claude is the priciest engine in the mix, the SerpAPI-backed engines the cheapest.

What the run budget means in cost terms

A single prompt-run across our 6 engines costs us about $0.25–$0.30 in API spend. The per-tier math falls out of total prompt-runs per week:

Starter: weekly cadence with up to 5 prompts = ~5 prompt-runs/week — roughly $65-80/yr in engine cost against $228/yr revenue. After payment processing, support, and infrastructure, this tier is priced to break even, not to fund the company.
Growth: each prompt runs 3× a week, up to 15 prompts = ~45 prompt-runs/week — roughly $585-700/yr in engine cost against $708/yr revenue at full utilization. Thin, and deliberately so: at realistic utilization (most Growth accounts run 5-10 prompts, not the full 15) the tier carries a workable margin.
Agency: daily runs with up to 50 prompts = ~350 prompt-runs/week. At full utilization the monthly cost circuit-breaker (below) is what keeps the tier viable; at realistic utilization the margin funds the priority support, white-label PDFs, and team seats.

We used to run Growth daily. At the measured cost per run, daily cadence on a full Growth prompt list cost more than the tier's price — the circuit-breaker would pause an engaged customer's runs mid-month, which is worse than an honest cadence. Three runs per prompt per week keeps trend lines tight (Mon/Wed/Fri-style spacing catches engine shifts within ~2 days) without the mid-month stop. Agency keeps true daily cadence.

So the founder's actual position on tier design is: Starter is priced to break even and let people testify whether the tool earns its keep. Growth is the workhorse — most customers should be on Growth. Agency funds the long-tail features (white-label, priority support, team seats) that don't pay for themselves on smaller tiers.

Why we're transparent about this

Most SaaS pricing pages either explain margins in abstract terms or stay quiet about cost structure entirely. We do it differently because the alternative — pretending Starter is a great deal you should stay on forever — leads to one of two bad outcomes:

You churn after a year because the value feels capped, and you blame the product.
You stay too long, get incomplete data, and conclude the whole tool category doesn't work.

Both are worse for you than us being clear: Starter is for validation. Growth is for actual ongoing use. If five prompts a week is the data you need, fine — but most teams need more.

What this means for your data quality

Starter's weekly cadence has real implications next to Growth's 3×/week and Agency's daily refresh:

You get fewer data points per week than a Growth or Agency customer. Trend lines stabilize slower. Detecting a real movement takes more weeks.
Sudden engine shifts can hide. If ChatGPT updates its default model on a Thursday and your next run is the following Monday, you see the post-change state, but you won't have a clean before-and-after. Growth's 3×/week cadence catches the shift within about two days; Agency's daily runs catch it inside 24 hours.
PR campaign attribution is harder. If you publish a major piece on day 1 and want to see Perplexity uptake, one run a week shows you a coarse signal. Growth's 3×/week gives you a usable curve; Agency's daily runs give you closer-to-real-time.

None of this is fatal. Plenty of solo founders run on Starter and get value. But if you're trying to attribute specific actions to specific data movements, the faster cadence on Growth is meaningfully more useful.

Manual runs

On every paid tier, you can trigger a manual Run now on any prompt. Manual runs draw from the same run budget as scheduled runs — the scheduler counts every prompt-run made today, manual or scheduled, against your day's allotment. Click Run now at 9am and the 06:00 UTC scheduler simply has one less run to make tomorrow morning; you're choosing when your budget is spent, not spending extra.

Three guardrails keep manual runs from running away:

A request limit of 5 run requests per 30 seconds per account.
A concurrency cap on simultaneous in-flight runs: 2 on Starter, 5 on Growth, 10 on Agency.
The monthly cost circuit-breaker (below), which backstops everything.

Hit any of these and the app tells you plainly; wait a moment and run again.

Hard caps that protect you

Two guardrails keep cost predictable for you and survivable for us:

Tier run cap: The number of scheduled prompt-runs you can spend per day is fixed by your tier (Starter spreads its 5 weekly runs across the week; Growth runs each prompt 3× a week; Agency runs every day with a higher per-day prompt budget). Once your day's budget is used up, scheduled runs pause until the next day. Manual Run now clicks count against the same bucket.
Monthly cost circuit-breaker: If your account's engine spend in a calendar month crosses a hard dollar threshold ($12 on Starter, $45 on Growth, $260 on Agency by default), the system stops scheduling new runs and we'll reach out. The thresholds are set so that normal full use of your quota never trips them, and they're tunable per-account if you have a legitimate reason to go higher.

These guardrails exist for two reasons: protecting you from surprise charges, and protecting our cost structure from edge cases. Neither has bitten a real customer yet, but the breakers are wired.

When to upgrade

Three signals you should move from Starter to Growth:

You've used all 5 prompt slots for at least a month and you keep wanting to add more.
Your weekly cadence is hiding movement — you can tell because you find yourself clicking Run now more than once a week to fill in gaps. Growth's 3×/week refresh removes that friction.
You're using Geotally for client work, even informally. Growth's faster cadence pays for itself in client conversations.

Two signals you should move from Growth to Agency:

You're tracking more than 3 brands — Growth caps at 3.
You want white-label PDFs for client deliverables.

We don't push upgrades. The dashboard shows your current tier and what's available, and we'll email when you're approaching a limit. We won't auto-upgrade you.