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 |
| Remote deployment | On-prem and air-gapped options for remote or sensitive sites |
| Safety boundaries | Agents retrieve and draft; permits stay with people |
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.
- Version controlled documents before trusting HSE answers.
- Agents never replace permits or competent-person judgment.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot maintenance history lookup on one asset class.
- 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.
- Put controlled-document versioning in place before HSE Q&A.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the sovereign AI readiness score →
Where AI agents pay off in oil and gas
Oil and Gas 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.
- Maintenance history — retrieve prior work orders and failure patterns for a tag
- HSE Q&A — answer procedure and safety questions from controlled documents
- Permit support — assemble permit-to-work checklists for review
- Field documentation — draft shift reports and handover notes
A reference architecture for oil and gas agents
A maintenance agent resolves equipment tags and pulls work-order history through tools, while an HSE agent retrieves the controlled procedure and cites it. Field actions remain with qualified personnel under your permit regime.
- Site-scoped keys and document collections
- Read-first tools into CMMS, historian and ERP systems
- Offline-capable deployment for remote sites
- Approval gates for any field or safety action
Data governance and human oversight
Safety-critical answers must be traceable. Version the controlled documents that feed retrieval, keep site data inside the boundary, and never let an agent substitute for a permit or a competent person's judgment.
- Controlled-document versioning in the corpus
- Site and role scoping
- Audit logs for every query
- Human authority for safety-critical decisions
From pilot to production
Pilot maintenance history lookup on one asset class, then HSE Q&A with strict document control. Keep safety decisions out of scope entirely.
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 |
| Safety-critical authority | Stays with people and permits | Varies | You enforce it |
| Remote sites | On-prem and air-gapped deployment | 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 it work at remote sites?
Yes — on-prem and air-gapped deployment supports sites without reliable connectivity, with periodic updates to models and documents.
Can agents approve permits?
No. They can assemble checklists and retrieve procedures; permits remain with authorised people and your existing process.
How do we keep procedures current?
Own the document pipeline: publish revisions into the retrieval collection on your change schedule and retire superseded versions.