Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions (change the base URL) |
| Models | 30+ models from free to frontier tiers behind one API |
| Agent primitives | Function calling, JSON mode and streaming are live |
| Retrieval | Embeddings and RAG over your own corpus |
| Deployment | Plugsky cloud, VPC, on-prem or air-gapped |
| Pricing | Flat monthly self-serve plans with fair-use usage; see the live pricing page |
| CRM tools | Function calling into your CRM and calendar |
| Approval flow | Client-facing sends reviewed by licensed staff |
TL;DR
- Keep your OpenAI SDK — change the base URL and model name.
- 30+ models behind one API, from free chat models to frontier reasoning.
- Deployment options from hosted cloud to VPC, on-prem and air-gapped.
- Pilot qualification and listing Q&A for one office.
- Licensed agents approve all client communication.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot lead qualification with one office's listings.
- Create a Plugsky account and generate an API key (free plan, no card required).
- Point your OpenAI SDK at the Plugsky base URL and map your model names.
- Index the approved corpus with embeddings and keep retrieval role-scoped.
- Keep client communication behind licensed review.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in real estate
Real Estate teams do not lack ideas for agents; they lack a safe path from demo to production. The pattern below targets repetitive, document-heavy work where a human can check the output, which is where agents earn their place first. Treat the agent as a new team member with a narrow brief, explicit permissions and a probation period, and rollout becomes an operations exercise rather than a leap of faith.
- Lead qualification — capture budget, timeline and preferences, and route hot leads
- Listing Q&A — answer property questions from approved listing content
- Market summaries — draft area and comparable reports from data you supply
- CRM follow-up — prepare personalised follow-up drafts for agent approval
A reference architecture for real estate agents
A qualification agent gathers structured lead details and updates your CRM through tools, while a listing agent answers from approved content and flags questions it cannot ground. Licensed agents approve all client communication.
- Listing and market retrieval collections
- Tools into CRM, calendar and listing feeds
- Lead scoring and routing rules
- Approval before client-facing sends
Data governance and human oversight
Property and client data is personal and sometimes regulated. Keep retrieval scoped, log interactions, and make sure your advertising and fair-housing obligations are reflected in what the agent may say — review outputs rather than assuming.
- Scoped retrieval per market or office
- Audit logs for generated messages
- Human review before client communication
- Documented sources for market claims
From pilot to production
Pilot lead qualification and listing Q&A for one office. Measure response time and qualification quality, then extend to market summaries.
Keep the rollout reversible: run the agent in shadow mode alongside the current process, compare outputs on your own samples, and move it into the workflow only when the evidence holds. Document what you measured so expanding to the next team is a decision, not a hope.
Honest comparison
| Capability | Plugsky | Typical cloud AI API | Building in-house |
|---|---|---|---|
| API compatibility | Drop-in base URL change | Usually compatible | Full rewrite |
| Model access | 30+ models behind one API | Vendor's own catalogue | You host each model |
| Pricing | Flat monthly self-serve plans; see live pricing | Often per-token | GPU + ops cost |
| Deployment | Cloud, VPC, on-prem or air-gapped | Usually vendor cloud regions | You own the stack |
| Client advice | Human-owned; agents prepare | Varies | You enforce it |
| Listing content | Approved collections only | Varies | You curate it |
Frequently asked questions
Do we have to rewrite our application?
No. The chat completions API is OpenAI-compatible, so you change the base URL and model name and keep your existing SDK.
Is there a free plan?
Yes — the free plan includes two free AI models, plugsky-micro and plugsky-lite, with no credit card required.
How is pricing structured?
Self-serve plans are flat monthly with fair-use usage and no per-token charges; see the live pricing page for current plans.
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 endpoints are coming soon — check the docs before planning around them.
Can agents give valuations?
They can summarise data you supply, but valuations and advice should come from licensed professionals; label any estimate as unverified.
Can it write to our CRM?
Yes, through tool calls your team defines; keep write permissions narrow and log every update.
How do we stay compliant in advertising?
Ground outputs in approved listing content, avoid ungrounded claims, and keep a human review step before anything reaches the public.