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 support | Multilingual models with official-content grounding |
| Student data | Service-scoped access and 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.
- Pilot on published content before record-specific work.
- Keep admissions and record decisions with staff.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot student-services 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 which questions must escalate to staff.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in universities
Universities 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.
- Student services — answer questions about courses, deadlines and procedures
- Admissions — triage enquiries and prepare responses for staff review
- Research support — retrieve literature and internal knowledge with citations
- Campus operations — answer facilities, IT and policy questions for staff
A reference architecture for universities agents
A student-services agent retrieves from approved academic content and escalates record-specific questions, while a research agent returns cited sources. Decisions about admissions, grades or records stay with staff.
- Faculty and service scoped collections
- Tools into student information and service systems
- Multilingual content for international students
- Review gates for record-affecting actions
Data governance and human oversight
Student data is personal and often regulated. Keep processing in an approved environment, scope retrieval by service, and require staff review for anything that touches a student's record or status.
- Service-scoped access control
- Audit logs for student interactions
- No autonomous record changes
- Retention aligned with institutional policy
From pilot to production
Pilot student-services Q&A on published content, then admissions triage. Keep record actions with staff and evaluate answer quality each term.
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 |
| Student records | Staff-owned; agents escalate | Varies | You enforce it |
| Residency | Region choice plus sovereign deployment options | Varies by provider | You control |
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 access student records?
Only within the access you grant, and record-affecting actions should stay with staff. Scope retrieval and tools to the minimum data needed.
Can it support international students?
Yes — multilingual models are available; keep official translated content as the retrieval source for accuracy.
Is there a free option for evaluation?
The free plan includes two models with no card, which suits evaluation and small pilots; see the live pricing page for current plans.