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 | Contract review, document review, research summaries, draft first passes |
| Integration path | Connects to DMS, practice-management and e-discovery 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 |
| Compliance posture | SOC 2 Type II and ISO 27001 readiness in progress (not yet certified); validate evidence during diligence |
TL;DR
- Accelerate first-pass review; keep legal judgement with lawyers.
- Isolate matters and mirror ethical walls in access control.
- Confirm training exclusion and retention in the DPA first.
- Verify every citation against primary sources.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pilot on closed matters with a lawyer-owned evaluation set.
- Agree DPA terms: training exclusion, retention, deletion and subprocessors.
- Design matter-level isolation for keys, indexes and access control.
- Build against the OpenAI-compatible endpoint with audit logging.
- Verify citations and outputs against primary sources before use.
- Expand practice group by practice group after measuring review time saved.
Original data
Try it yourself
Open the prompt diff and evaluator →
Where an AI API fits in law firms
Legal work is reading, comparing and drafting under confidentiality. The API should accelerate the first pass and leave judgement with the lawyer:
- Contract review assistance: flag deviations from playbook positions for the associate to assess.
- Document review: classify and cluster large sets for responsiveness and privilege triage, with human confirmation.
- Research summarisation: condense cases, articles and commentary into referenced memos.
- Draft first passes: assemble clauses, letters and memos from firm precedents for lawyer editing.
- Billing narratives: turn time entries into clear narratives for partner review.
Security, privacy and data handling
Privilege is fragile: disclosure to the wrong place can waive it. The architecture should reflect that:
- Keep matter data isolated with separate projects, keys and retrieval indexes.
- Confirm training exclusion, retention and deletion in the DPA before indexing client files.
- Enforce access control that mirrors ethical walls, not just folder permissions.
- Require lawyer review before any output reaches a client or a filing.
Deployment options and model choice
Matter data usually belongs in a private or region-locked environment, with access controls that mirror your ethical walls. 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
Legal technology mistakes are often evidentiary, not embarrassing. Avoid:
- Indexing multiple matters in one retrieval space.
- Sending privileged material before the DPA and training exclusion are agreed.
- Treating generated research as verified authority without checking citations.
- Letting billing narratives overstate work performed.
- Rolling out firm-wide without a pilot on closed matters.
Pilot on closed matters with the DPA in place, verify citations against primary sources, and keep matter isolation and ethical walls enforced technically. Document the review steps so the process is defensible.
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 | Contract review, document review, research summaries, draft first passes | 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.
Does using an AI API waive privilege?
That depends on jurisdiction, terms and how the tool is used. Get legal and ethics advice for your circumstances; confidentiality terms in the DPA are necessary but not sufficient.
Can client data be used for training?
Plugsky processes customer data to provide the service; training exclusion belongs in your DPA. Confirm current terms with the enterprise team before indexing client files.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover isolation, residency 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 it replace associates?
No. It reduces time on first-pass review and drafting; lawyers remain responsible for advice, strategy and sign-off.