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 |
| Multilingual service | Multilingual models with official-content grounding |
| Oversight | Identified requests and exportable audit logs |
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.
- Ground public answers in official content only.
- Make agent activity auditable for oversight.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot multilingual Q&A on published content.
- 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 review rules for anything public or case-specific.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the AI data residency checklist →
Where AI agents pay off in the public sector
Public Sector 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.
- Service desk — answer common questions from official content, in multiple languages
- Records requests — help staff locate and assemble responsive material
- Procurement research — summarise specifications and compare supplier submissions
- Internal knowledge — surface policies and procedures for frontline teams
A reference architecture for the public sector agents
A service agent retrieves from an approved public-content collection and escalates anything case-specific, while a procurement agent summarises submissions against criteria for evaluation teams. Decisions and publications stay with accountable officers.
- Department-scoped keys and retrieval
- Tools into service desk and records systems
- Multilingual content collections
- Review gates and full audit trails
Data governance and human oversight
Accountability is the design driver. Keep processing in the approved boundary, publish only reviewed content, and make agent activity auditable end to end.
- Department-scoped access
- Audit logs exportable for oversight
- Human review before any public communication
- Data minimisation in retrieval
From pilot to production
Pilot multilingual service-desk Q&A on published content, then records support. Keep case-specific decisions outside the agent's authority.
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 |
| Accountability | Audit logs and review gates | Varies | You configure |
| Public communication | Reviewed before publication | 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 agents answer citizens directly?
Only from approved public content and under your communication policy; anything case-specific or discretionary should route to staff.
How do we handle multiple languages?
Multilingual models are available; keep official translations as the retrieval source so accuracy does not depend on generation alone.
Is agent activity available for oversight?
Every request can carry an identity and produce logs, which supports audit and public-records processes.