Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions; drop-in base URL change |
| Models | 30+ models behind one API; open-weight options for private deployment |
| Typical patterns | Ticket summaries, runbooks, client reports, white-label assistants |
| Integration path | Connects to PSA, RMM, documentation and reporting platforms via middleware |
| Pricing model | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing — see the live pricing page |
| Free tier | plugsky-micro and plugsky-lite on the free plan, no card required |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Identity and audit | SSO/SCIM, role-based access, SIEM audit log export and BYOK via KMS or HSM |
TL;DR
- Design tenancy first: keys, indexes and audit per client.
- Keep credentials and secrets out of prompts entirely.
- Report in plain language from verified monitoring data.
- Confirm white-label and residency terms before reselling.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pilot on internal service tickets before any client data.
- Design per-tenant keys, namespaces and retrieval indexes.
- Keep credentials, secrets and unnecessary client data out of prompts.
- Build against the OpenAI-compatible endpoint with per-tenant audit logging.
- Agree white-label and residency terms with the enterprise team.
- Roll out client by client, measuring handling time and satisfaction.
Try it yourself
Open the rate limit calculator →
Where an AI API fits in MSPs
An MSP's economics depend on doing more per technician without breaching client trust. The API helps when tenancy is designed in:
- Ticket triage and summaries: classify and condense tickets so technicians start with context.
- Runbook generation: draft standard procedures from resolved tickets for senior review.
- Client reporting: turn monitoring and service data into plain-language monthly summaries.
- Onboarding documentation: draft environment documentation from discovery notes.
- White-label assistants: embed an assistant into your own portal under your brand.
Security, privacy and data handling
Every client is a separate trust boundary, so isolation must be architectural:
- Separate keys, namespaces and retrieval indexes per client tenant.
- Keep credentials and secrets out of prompts; models propose, technicians execute.
- Give each client an audit view so access questions are answerable.
- Match residency and deployment to the strictest contract you serve.
Deployment options and model choice
Run a single platform with per-tenant keys and indexes, and choose the strictest residency tier your client contracts require. Plugsky exposes the same OpenAI-compatible endpoint whether the workload runs in shared cloud, your VPC, on-prem or air-gapped, and region-locked planes keep processing where your policy requires. Teams route to 30+ models through one API, with open-weight options when a site has no external connectivity, and port code with a base URL change. Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live; audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon. plugsky-micro and plugsky-lite are free with no card, a 14-day full-access trial covers paid tiers, and the live pricing page lists current plans.
From pilot to production
Cross-tenant incidents end MSP relationships. The usual causes:
- One shared key or knowledge index across all clients.
- Sending client credentials or configuration into prompts.
- No per-client audit trail when a client asks who did what.
- Assuming your own privacy policy satisfies every client contract.
- Reselling before the white-label terms are agreed.
Build the tenant model first, pilot on your own internal tickets, and only then productise for clients. Keep per-client keys, indexes and audit views, and confirm white-label and residency terms before launch.
Honest comparison
| Capability | Plugsky | Typical per-token API | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible chat, embeddings and tools | Usually compatible | Full rewrite |
| Deployment | Cloud, VPC, on-prem and air-gapped | Mostly cloud-only | You operate GPUs and serving |
| Data residency | Region selection and sovereign options | Limited regions | You control fully |
| Pricing | Flat monthly self-serve, fair-use usage | Per-token, harder to forecast | GPU plus operations cost |
| Model choice | 30+ models behind one API | Varies by provider | You host every model |
| Industry fit | Ticket summaries, runbooks, client reports, white-label assistants | Generic API, you adapt it | You build every workflow |
Frequently asked questions
Can we keep our existing OpenAI SDK code?
Yes. Plugsky exposes an OpenAI-compatible API, so you change the base URL and model name and keep your integration.
Is there a free plan?
Yes. The free plan includes two free models, plugsky-micro and plugsky-lite, and does not require a credit card.
How do we isolate clients?
Use separate projects and keys per client, separate retrieval indexes, and per-tenant audit logs. Isolation belongs in the architecture, not only the policy.
Can we resell AI under our own brand?
Plugsky offers a white-label AI API option. Confirm packaging, support and terms with the enterprise team before reselling.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise and white-label agreements cover capacity and SLA terms. See the live pricing page for current plans.
Which endpoints are live today?
Chat completions, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon.
Can we meet different residency requirements per client?
Region-locked planes let you select where processing happens; enterprise options include VPC, on-prem and air-gapped deployment for stricter contracts.