How Credits Work
Every credit charge reflects actual compute consumed. No model gating, no silent throttling, no quality trade-offs.
Why metered billing
A 12-page teaser and a 200-page OM with a rent roll and T-12 are not the same compute job. The variance across document types is around 15x. A flat subscription collapses that into a single monthly rate, which means someone absorbs the difference on every complex deal you run.
That someone is usually you. When a vendor is losing money on your large deals, they recover it somewhere: a smaller model, truncated context, a monthly document cap you only discover when you hit it. You rarely see it happening. The extraction just looks a little worse on the 80-page packages.
We bill per unit of compute because it is the most direct way to align incentives. A large deal costs more credits than a small one. It also gets the same model, the same context window, and no background quality floor. That is the trade.
The formula
| Parameter | Description |
|---|---|
| Unit Cost | Per-unit rate, varies by operation type and model tier |
| Quantity | Pages parsed or tokens consumed, depending on operation |
| $0.01 | Credit denomination (one cent per credit) |
Cache reads: When the same document is queried multiple times in a session, cached token rates apply. These are meaningfully cheaper than re-reading the full context from scratch.
Operation reference
Every operation that consumes credits, and what triggers it in the workflow. Exact unit rates are shown in your account under Usage.
| Operation | Triggered by | Unit | Billed at |
|---|---|---|---|
| Document parse | Uploading an OM, rent roll, or T-12 | Page | 1 credit / page |
| AI extraction (input) | Field extraction begins after parsing | 1K tokens | Per 1K tokens |
| AI extraction (output) | Structured deal data returned | 1K tokens | Per 1K tokens |
| Cache read | Same document queried again in session | 1K tokens | Reduced rate |
| Comps & market data | Comparable sales or rent comps pulled | Per query | Per query |
| LOI / report generation | LOI draft or investment memo requested | 1K output tokens | Per 1K tokens |
| Q&A chat | Conversational query on deal data | Tokens | Per token |
What is included per plan
Credits are account-pooled. Your whole team draws from one shared monthly balance.
| Plan | Credits / seat / mo | Est. full pipeline runs | Price | Overage rate |
|---|---|---|---|---|
| Starter | 500 | ~3–5 | $199/seat/mo | $0.05/credit |
| Growth | 1,500 | ~8–12 | $349/seat/mo | $0.04/credit |
| Professional | 5,000 | ~30+ | $799/seat/mo | $0.03/credit |
| Enterprise | Custom | Custom | Contact us | By contract |
One full pipeline run includes: parse + AI extraction + comps pull + LOI draft. Quick screens (parse and extraction only) consume fewer credits. Simple Q&A consumes the least.
Frequently asked questions
Ready to underwrite smarter?
Every credit goes toward actual AI compute on your deal — no hidden limits, no model downgrade, no surprises.