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 | Quality summaries, SOP Q&A, maintenance knowledge, supplier comms |
| Integration path | Connects to MES-adjacent, QMS, EAM and ERP systems 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
- Start with document Q&A and reviewable summaries on the line.
- Keep AI infrastructure separate from OT and production control.
- Index controlled documents only, with revision awareness.
- Put prompts under change control for reproducibility.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pick one document domain, such as SOPs or maintenance procedures.
- Build a revision-controlled index of approved documents.
- Choose private or on-prem deployment if process data is involved.
- Build against the OpenAI-compatible endpoint with controlled interfaces.
- Put prompts and evaluations under change control.
- Validate with engineers on real documents, then expand.
Try it yourself
Open the LLM GPU capacity calculator →
Where an AI API fits in manufacturing
Factory value comes from fewer surprises and faster answers on the line. Start with documents and reviewable drafts:
- Quality report summaries: condense inspection data and non-conformance notes into reviewable summaries for engineers.
- SOP and manual Q&A: answer operator and technician questions from the current controlled document.
- Maintenance knowledge: surface prior work orders and procedures for an asset id.
- Supplier correspondence: summarise long email threads and 8D reports into action lists.
- Production-planning analysis: turn shift and output notes into structured commentary for planners to verify.
Security, privacy and data handling
Factories blend IT and OT, so the AI layer must respect the boundary and the controlled-document regime:
- Keep AI infrastructure out of OT networks and treat it as untrusted relative to control systems.
- Use on-prem or private deployment for process and product data.
- Index controlled documents only, with revision awareness.
- Keep engineers accountable for quality and safety decisions.
Deployment options and model choice
Plant and process data belongs on-prem; corporate documentation can run in region-locked cloud. 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
Manufacturing punishes undocumented change. Common mistakes:
- Letting the model answer from superseded SOP revisions.
- Connecting the API to production systems without controlled interfaces.
- Treating generated quality commentary as a released record.
- Sending product and process IP to shared endpoints against policy.
- Changing prompts without change control, then losing reproducibility.
Pick one document domain, build a revision-controlled index, and keep prompts under change control from day one. Validate on real production documents and require engineering sign-off before expansion.
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 | Quality summaries, SOP Q&A, maintenance knowledge, supplier comms | 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.
Can it run on-premises?
Yes. On-prem and air-gapped deployment are available for enterprise setups where production data cannot leave the facility.
Will it connect to our MES or SCADA?
Do not connect directly to control systems. Integrate through middleware with controlled interfaces and keep AI in the information layer.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover private deployment 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.
How do we keep answers current?
Index only released revisions, expire superseded documents from retrieval, and re-run evaluations whenever a controlled document changes.