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 |
| Playbook support | Deviation checks against your standard positions |
| Access control | Role-scoped retrieval for legal and privileged content |
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.
- Keep privileged material in its own collection and keys.
- Agents triage and summarise; counsel approves.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Start with policy Q&A, then playbook-based contract triage.
- 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.
- Define which outputs require counsel approval before launch.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the AI data residency checklist →
Where AI agents pay off in legal teams
Legal 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.
- Contract review — compare incoming paper against your playbook and flag deviations
- Policy Q&A — answer business questions from approved policies
- Obligations — extract dates and duties from agreements into a tracker
- Regulatory summaries — digest updates you supply and map them to internal owners
A reference architecture for legal teams agents
A review agent compares contract text to your standard positions and lists exceptions, while a Q&A agent retrieves policy answers with citations. Counsel approves anything that binds the company or changes a position.
- Business-unit scoping for retrieval
- Tools into CLM, ticketing and document stores
- Playbook configuration and deviation reports
- Review gates for obligations and external communications
Data governance and human oversight
Privilege and confidentiality drive the design. Keep legal content in a restricted collection, limit access by role, log queries, and make clear internally that agent output is not legal advice until counsel adopts it.
- Role-scoped access to legal collections
- Audit logging of queries and tool calls
- Review before obligations are recorded
- Retention and deletion per matter type
From pilot to production
Start with policy Q&A for the business and playbook-based contract triage, then extend to obligation extraction once precision is measured against counsel review.
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 |
| Privileged work | Separated collections and keys | Varies | You configure |
| Approvals | Counsel-owned; agents prepare | Varies | You enforce it |
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 the agent approve contracts?
No. It can review against your playbook and flag deviations; only authorised counsel should approve or execute.
Can business teams use it directly?
Yes, for policy questions and first-pass triage, with clear guardrails on what the agent may say and an escalation path to counsel.
How do we keep privileged material separate?
Use dedicated collections and keys for privileged work, and keep them out of broader business-facing retrieval.