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 |
| Program isolation | Separate keys and retrieval collections per program |
| Long context | Long-context models available for large excerpts |
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.
- Isolate programs before indexing any documents.
- Drafting support only with specialist sign-off.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot internal retrieval with program scoping.
- 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.
- Validate citation accuracy before drafting workflows.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in pharmaceuticals
Pharmaceuticals 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.
- Regulatory Q&A — answer process and guideline questions from approved sources
- Document drafting — assemble sections from templates and source material
- Literature monitoring — summarise new publications you supply for review
- Program knowledge — surface prior submissions and internal reports quickly
A reference architecture for pharmaceuticals agents
A knowledge agent retrieves from a program-scoped collection and cites sources, while a drafting agent fills templates for specialists to verify. Nothing enters a submission, label or safety process without qualified review.
- Program-scoped retrieval and keys
- Tools into document management systems
- Template and citation controls
- Review gates and audit logs for regulated outputs
Data governance and human oversight
Regulated content needs traceability and controlled access. Link every statement to its source, keep programs isolated, and retain logs so reviewers can reconstruct how a draft was produced. Specific compliance obligations remain yours to interpret.
- Citation-linked drafts
- Program and role isolation
- Audit trails for generated content
- Qualified sign-off before any regulatory use
From pilot to production
Pilot internal knowledge retrieval and literature summaries, then drafting support. Measure citation accuracy against specialist review before expanding.
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 |
| Traceability | Source-linked citations | Varies | You build it |
| Program separation | Scoped collections and keys | Varies | You configure |
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 agents prepare regulatory submissions?
They can draft from approved templates and sources; qualified specialists must verify and own any submitted content.
How is confidential program data isolated?
Use separate keys and retrieval collections per program so an agent only reaches the material its task allows.
Does it handle long documents?
Long-context models in the catalogue can take large excerpts; for whole document sets, retrieval plus summarisation is usually more reliable.