Every listing from scratch
Same bedrooms, same square footage fields, and still an hour to write something that does not sound like every other listing.
For agents, brokerages and proptech
List it, lease it, close it faster
Listing copy that sells the light in the kitchen, lease abstracts that surface the break clause, follow-ups that land while the buyer is still excited. All from one endpoint.
Listings in minutes
from property notes to polished copy
Lease abstracts
key terms pulled into one page
Timely follow-ups
drafted right after the viewing
The problem
What is slowing you down today
Leases nobody wants to read
Rent reviews, break options and repair obligations buried across forty pages.
Leads that go cold
The viewing went well. The follow-up went out three days later.
Capabilities
Everything you need, nothing you don't
Listing descriptions
Send features, neighbourhood notes and tone, get headline and body copy for each portal.
Lease abstraction
Extract parties, term, rent, review dates, break clauses and repair obligations as a structured summary.
Follow-up drafts
Personalised notes after viewings and open houses, based on what the buyer actually said.
Built for proptech
One authenticated endpoint with per-call pricing, so your platform knows the cost of every generated listing.
Cache for repeat templates
Identical prompts inside the cache window return instantly and are not billed.
Always the right fit
The router picks the lowest-priced model with the capability you request.
Use cases
What teams run on it
01
Portal listing copy
Variants sized for each portal and your own site.
02
Commercial lease summaries
A one-page abstract for asset managers and lenders.
03
Buyer and tenant follow-ups
Next-day emails that reference the viewing and next steps.
04
Neighbourhood guides
Local area overviews drafted from your own notes and data.
How it works
From sign-up to production
- 1
Write a listing in the playground
Paste your property notes and see the result and its price.
- 2
Connect your CRM or platform
Call the endpoint with an API key from your workflow.
- 3
Roll out across the office
Track daily and month-to-date usage in the dashboard.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Will listings sound generic?
Give it your agency's tone and a couple of past listings you love. It writes from what you send.
Can it read a full lease?
Send the lease text in the prompt and ask for the fields you need. Very long documents may need splitting into sections.
Is it accurate enough to rely on?
Treat output as a draft. Have a qualified person check abstracts and listing claims before they are used.
What does a listing cost?
Each response shows its exact price. The catalog lists per-token prices for every model.
Spend your time at viewings, not keyboards
Write your next listing free. See the price before you scale.