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 |
| Channel flexibility | Per-channel prompts and model selection |
| Commerce tools | Read-first integration with order systems |
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 one category and measure deflection.
- Keep refunds and pricing under system control.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot product Q&A on a single category.
- 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.
- Define refund and pricing guardrails before order support.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in retail
Retail 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.
- Product Q&A — answer sizing, compatibility and availability questions from catalogue data
- Order support — check status and prepare changes through commerce tools
- Returns triage — classify reasons, apply policy and route exceptions
- Store operations — answer process questions for staff from SOPs
A reference architecture for retail agents
A shopper agent retrieves from the product catalogue and checks orders through tools, while a returns agent applies your policy and escalates edge cases. Refunds and price overrides stay with staff or your rules engine.
- Catalogue and policy retrieval collections
- Tools into commerce, OMS and ticketing
- Policy-aware routing and escalation
- Per-channel prompts and model choices
Data governance and human oversight
Customer and payment data require care. Keep retrieval scoped, avoid exposing order details beyond what the task needs, and log interactions for dispute handling.
- Minimal data exposure per task
- Audit logs for customer interactions
- No autonomous refunds or pricing changes
- Retention aligned with commerce policy
From pilot to production
Pilot product Q&A on one category, then order support. Measure deflection and escalation quality before extending to returns.
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 |
| Commerce systems | Agents call them via tools; they stay authoritative | Varies | You integrate |
| Refunds | Rules-engine or staff approval | Varies | You enforce 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 the agent process refunds?
It can classify and prepare; refunds should execute under your rules with staff or system approval.
Can it recommend products?
It can answer and suggest from your catalogue content; keep recommendations grounded so they reflect real stock and policy.
Does it handle peak traffic?
Plan capacity with your provider and use rate limits per key. See the status page for live component health.