Key facts
| API compatibility | OpenAI-compatible chat, embeddings and function calling |
| Use cases | Listing copy, property Q&A, contract and disclosure extraction, lead qualification |
| Data controls | Scoped API keys, RBAC, SSO, audit logs and region selection |
| RAG | Index listings, disclosures and policy documents so answers cite the source |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Models | 30+ models from free aliases to frontier reasoning |
| Pricing model | Flat monthly self-serve plans with unlimited fair-use usage |
| Free tier | plugsky-micro and plugsky-lite on the free plan, no card required |
TL;DR
- Draft listing copy from structured property data in a consistent voice.
- Answer buyer questions with citations to the listing, disclosures and rules.
- Extract fields from contracts and disclosure packs for agent review.
- Score and route inbound leads before an agent spends time on them.
- Keep payment and identity data out of prompts; configure keys and logs first.
How it works, step by step
- Start with listing copy: feed structured property facts and generate a draft for the agent to edit.
- Index listings, disclosures and office policy so Q&A can cite the exact source.
- Extract key fields from contracts and disclosure packs into your CRM for review.
- Scope API keys per channel (website, portal, CRM) and enable audit logging.
- Set the processing region and retention to match your client privacy commitments.
- Measure draft edit time and lead routing accuracy, then expand to the next workflow.
Try it yourself
Open the LLM token calculator →
Real estate workflows that benefit first
Most real estate text is repetitive and data-driven, which suits constrained AI tasks:
- Listing copy: turn structured facts into a description in the office's tone, then let the agent polish.
- Property Q&A: answer questions from a listing page with citations to the listing and disclosure documents.
- Document extraction: pull parties, dates, amounts and contingencies out of contracts into your CRM.
- Lead qualification: classify intent, budget band and urgency, and route to the right agent.
Keep the licensed agent accountable for anything that is advice or a representation.
Security and client data
The sensitive material is client identity, financial details, access information and transaction documents. Configure scoped API keys per integration, RBAC and SSO for staff, and audit logs so every request is attributable. Select the processing region and set retention deliberately, and keep payment credentials and government identifiers out of prompts. If a brokerage or client contract demands stronger separation, isolate at the deployment level with a VPC or on-prem install. Plugsky provides the controls; your brokerage policy still governs what can be sent.
Deploy once, run anywhere
Because Plugsky uses the OpenAI-compatible API shape, a prototype built for one office moves to a regional or national rollout without rewriting integrations. The same retrieval code and prompts work in the cloud, in your VPC, on-prem or air-gapped. Use plugsky-embed for retrieval over listings and disclosures, a small model for classification and lead scoring, and a stronger model only for customer-facing drafts. Keep stable document ids so citations resolve in the UI.
From prototype to rollout
Prototype free with plugsky-micro or plugsky-lite on a single office's listings, then use the 14-day full-access trial to compare frontier models on customer-facing copy. Metrics worth tracking: edit minutes per listing, lead routing accuracy, extraction error rate and unanswered-question rate. Self-serve plans are flat monthly with fair-use usage, so high listing seasons do not create billing surprises. Roll out per office with versioned prompts, and re-test whenever your disclosure templates change.
Honest comparison
| Capability | Plugsky | Typical per-token API | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible chat, embeddings and tools | Usually compatible | Full rewrite |
| Access control | Scoped API keys, RBAC, SSO and audit logs | Varies by provider | You build all of it |
| Deployment | Cloud, VPC, on-prem and air-gapped | Mostly cloud-only | You operate GPUs and serving |
| Pricing | Flat monthly self-serve, fair-use usage | Per-token, harder to forecast | GPU plus operations cost |
| Model choice | 30+ models behind one API | Varies by provider | You host every model |
Frequently asked questions
Can we keep our existing OpenAI SDK code?
Yes. Plugsky is OpenAI-compatible, so you change the base URL and model name and keep your current SDK and integrations.
Is there a free plan?
Yes. The free plan includes plugsky-micro and plugsky-lite with no credit card, enough to test listing copy and property Q&A.
How do we keep answers accurate?
Index the listing, disclosures and office policy with embeddings, retrieve the relevant passages, and require citations so the agent can verify the source.
Can the AI give advice to buyers?
It can draft and retrieve, but a licensed agent should review anything that could be read as advice or a representation about a property.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage. See the live pricing page for current plans and enterprise options.
Can we deploy in our own environment?
Yes. VPC, on-prem and air-gapped options are available for brokerages and clients that restrict where data is processed.
Which endpoints are live today?
Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and responses are coming soon.