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 |
| Allergen safety | Ground answers in a controlled, versioned allergen source |
| Booking tools | Function calling into reservation platforms |
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.
- Curate allergen content before enabling menu Q&A.
- Escalate uncertainty to staff; never improvise on safety.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Curate and version allergen content first.
- 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.
- Pilot reservation Q&A and review drafts.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the LLM token calculator →
Where AI agents pay off in restaurants
Restaurants 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.
- Reservations — answer availability and policy questions and prepare changes
- Menu Q&A — handle ingredient and allergen questions from approved content
- Reviews — draft on-brand replies for manager approval
- Suppliers — retrieve and summarise order and specification documents
A reference architecture for restaurants agents
A guest agent answers from your approved menu content and prepares reservation changes through tools, while a reviews agent drafts replies. Allergen answers must be grounded in your controlled data, never generated from memory.
- Menu, allergen and policy retrieval collections
- Tools into reservation and ordering platforms
- Escalation to staff for allergy or complaint cases
- Approval before any guest compensation
Data governance and human oversight
Allergen and dietary information is a safety matter. Keep it in a controlled, versioned collection, require grounding in that source, and escalate any uncertainty to staff.
- Versioned allergen content
- No generated allergen claims
- Audit logs for guest interactions
- Manager approval for refunds or comps
From pilot to production
Pilot reservation questions and review drafts, with allergen content curated first. Only enable menu Q&A once the controlled source is complete.
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 |
| Safety content | Controlled, versioned source required | Varies | You maintain it |
| Bookings | Prepared via tools; platform stays authoritative | Varies | You integrate |
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 it answer allergen questions?
Only from a controlled allergen source you maintain, and it should escalate uncertainty to staff. Never let it improvise on allergens.
Does it connect to our booking system?
Through tool calls you define — your integration wires the reservation platform and keeps it authoritative.
Can it reply to reviews?
It can draft replies in your voice for a manager to approve; publishing should stay a reviewed action.