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 | MRO doc search, parts Q&A, training drafts, publication summaries |
| Integration path | Connects to MRO, ERP and document-management systems through 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
- Use the API to find and summarise approved documents, not to improvise.
- Index current revisions only and cite the source in every answer.
- Keep airworthiness decisions with licensed personnel.
- Deploy on-prem or air-gapped where technical data must not leave.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pick one document domain, such as MRO procedures or parts catalogues.
- Build a revision-controlled index and exclude superseded documents.
- Define role-based retrieval filters before any user access.
- Build against the OpenAI-compatible endpoint and log retrieval sources.
- Choose the deployment tier and region the data classification requires.
- Pilot with named engineers who approve outputs, then expand domain by domain.
Original data
Try it yourself
Open the private LLM deployment estimator →
Where an AI API fits in aviation
Aviation runs on controlled documentation: manuals, service bulletins, airworthiness directives and training records. The API should help people find and summarise approved content, never replace the approved source:
- MRO manual search: answer 'where is this procedure' questions with citations to the current revision.
- Parts catalogue Q&A: map part numbers, alternates and effectivity from approved catalogues.
- Publication summaries: condense long regulatory and manufacturer documents into review checklists for engineers.
- Training material drafts: turn approved source content into draft modules that instructors edit and approve.
- Operations correspondence: summarise vendor and authority correspondence into action lists with owners.
Security, privacy and data handling
Documentation integrity is the whole point in aviation, so controls centre on provenance, access and traceability:
- Ground every answer in approved, version-controlled documents with citations.
- Restrict retrieval by role so staff only reach the documentation their authorisation covers.
- Keep airworthiness and maintenance-release decisions with licensed personnel.
- Log prompts, outputs and the document revision each answer relied on.
Deployment options and model choice
Where technical data cannot leave the facility, on-prem or air-gapped tiers replace cloud without changing the API shape. Deployment is a choice among four tiers on the same OpenAI-compatible API: shared cloud, a private endpoint in your VPC, on-prem and air-gapped, with region selection for residency. The catalogue holds 30+ models behind one key, with open-weight models for disconnected sites, and switching provider is a base URL change. Live today: chat, streaming, JSON mode, function calling, embeddings, RAG and agents. Still coming soon: audio, images, moderation, files, batch, fine-tuning, assistants and the responses API. Start on the free plan with plugsky-micro and plugsky-lite, no card, or use the 14-day full-access trial for paid tiers; the live pricing page has current plans.
From pilot to production
In a regulated documentation environment, the risky shortcuts are organisational rather than technical:
- Letting the model answer from memory instead of the approved revision.
- Indexing superseded documents without a revision filter.
- Giving every user the same broad retrieval access.
- Treating a generated checklist as an approved inspection procedure.
- Piloting without a named accountable engineer and an approval record.
Choose one documentation domain, index only current revisions, and require engineers to cite and approve outputs. Traceability (who asked, what was retrieved, which revision, who approved) is the acceptance criterion, not answer fluency.
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 | MRO doc search, parts Q&A, training drafts, publication summaries | 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 and prompts.
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 the API replace approved maintenance documentation?
No. It should retrieve and summarise approved documents with citations. The approved revision remains the source of truth and licensed personnel remain accountable.
Can it run without internet access?
Yes. Air-gapped deployment is available for enterprise setups where no traffic may leave the environment; on-prem is an option where connectivity is constrained.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover private and air-gapped deployment. 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 prove traceability?
Log the user, prompt, retrieved documents and revisions, model version and approver for every assisted output, and export audit logs to your SIEM.