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 |
| Network safety | Read-first access; change control stays with engineering |
| Incident data | Draft updates from incident information you supply |
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 NOC runbook lookup before care automation.
- No autonomous network changes, ever.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot runbook lookup in the NOC.
- 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 network changes under engineering approval.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in telecom
Telecom 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.
- Care triage — classify customer issues and run guided diagnostics
- Outage communications — draft status updates from incident data
- Runbook lookup — retrieve NOC procedures for the tapped alarm
- Field support — answer installation and configuration questions on site
A reference architecture for telecom agents
A care agent runs guided diagnostics through tools and drafts the resolution, while a NOC agent retrieves the matching runbook and summarises alarm context. Network changes remain under engineering change control.
- Per-team keys with strict scopes
- Retrieval over runbooks, topology docs and service catalogues
- Read-first tools into OSS/BSS, ITSM and monitoring
- Approval gates before network or billing changes
Data governance and human oversight
Telecom data is personal and network data is critical. Keep processing in the approved boundary, log every action, and keep agents out of any change path that lacks engineering approval.
- Role-scoped access to network data
- Audit trails for diagnostics and drafts
- No autonomous network changes
- Retention aligned with telecom obligations
From pilot to production
Pilot runbook lookup in the NOC and care triage for one product. Measure resolution accuracy and escalation quality before expanding.
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 |
| Network changes | Engineering change control | Varies | You enforce it |
| On-prem fit | VPC, on-prem and air-gapped options | Often cloud-only | You own the stack |
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 change network configuration?
No. They retrieve, summarise and draft; changes stay under engineering change control.
Can it handle many languages for care?
Yes — multilingual models are available; ground policy answers in official content to keep them accurate.
Can it work on-premises?
Yes — Plugsky supports VPC, on-prem and air-gapped deployment for network-adjacent workloads.