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 | Asset doc search, maintenance summaries, permit digests, HSE drafts |
| Integration path | Connects to EAM, GIS, SCADA-adjacent archives and document 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 |
| Compliance posture | SOC 2 Type II and ISO 27001 readiness in progress (not yet certified); validate evidence during diligence |
TL;DR
- Start with documentation and HSE support, not control or protection.
- Segment AI infrastructure from OT and treat it as untrusted.
- Prefer region-locked or on-prem deployment for operational data.
- Verify every environmental or safety figure before publication.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Map candidate use cases to assets and classify consequence of failure.
- Select deployment and residency per data class: cloud, VPC, on-prem or air-gapped.
- Segment AI infrastructure from OT with explicit boundary controls.
- Define and rehearse degraded modes for every assisted process.
- Implement scoped keys, key custody and audit export.
- Validate on representative documents, then expand with a change process.
Original data
Try it yourself
Open the self-hosting break-even calculator →
Where an AI API fits in energy
Energy produces decades of technical text and a steady stream of regulatory obligations. Grounded retrieval is the strongest starting point:
- Asset document search: find drawings, procedures and inspection history for a specific asset with citations.
- Maintenance summaries: condense work orders and inspection reports into reviewable condition summaries.
- Permit and obligation digests: extract dates, limits and reporting duties from permits and correspondence.
- Outage and HSE communications: draft status and incident communications from verified facts for approval.
- Shift handovers: structure operational notes into consistent handovers the incoming team confirms.
Security, privacy and data handling
Energy combines critical infrastructure with personal and market-sensitive data, so segmentation and evidence are baseline expectations:
- Keep AI infrastructure in its own zone, separated from OT and control networks.
- Prefer private or on-prem deployment where operational data cannot leave the site.
- Restrict market-sensitive and personal data to workflows with a documented basis.
- Log every request and define degraded-mode behaviour for assisted processes.
Deployment options and model choice
Keep corporate documentation in region-locked cloud and put plant or grid data on-prem where policy or connectivity demands it. The same OpenAI-compatible API runs across Plugsky cloud, a private endpoint in your VPC, on-prem and air-gapped, with region-locked planes for residency. One key reaches 30+ models, including open-weight options for offline deployment, and migration is 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 remain coming soon. The free plan includes plugsky-micro and plugsky-lite with no card, and a 14-day full-access trial covers paid tiers — see the live pricing page for current plans.
From pilot to production
The risks in energy are physical and regulatory, so avoid shortcuts that blur the boundary:
- Connecting the API to OT networks or control systems in any form.
- Sending grid or plant data to shared endpoints against policy.
- No manual fallback when AI-assisted processes are unavailable.
- Publishing environmental or safety figures that nobody verified.
- Treating a corporate pilot as approval for operational deployment.
Keep the first phase in corporate and documentation functions, run a consequence-of-failure review before any operational expansion, and rehearse degraded modes. Keep an asset-mapped register of approved use cases.
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 | Asset doc search, maintenance summaries, permit digests, HSE drafts | 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 code across tiers.
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 operational data stay on-premises?
Yes. On-prem and air-gapped deployment are available for enterprise setups where data cannot leave the site; region-locked cloud covers other cases.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover private deployment, residency and SLA terms. See the live pricing page for current plans.
Is Plugsky certified?
SOC 2 Type II and ISO 27001 readiness are in progress rather than completed. Track that status in your risk register and validate compensating controls.
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 should we start?
Pick a corporate documentation workflow, prove accuracy on real documents, and expand only after a safety and security review approves each new use case.