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 |
| Multi-tenancy | Per-tenant keys and separated retrieval collections |
| Pricing model | Flat monthly self-serve plans with fair-use usage |
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.
- Enforce tenant isolation by key and collection.
- Ship a copilot on flat self-serve pricing.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot on internal accounts, then a design-partner tenant.
- 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.
- Prove tenant isolation before general availability.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in SaaS
SaaS 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.
- In-app copilot — answer product questions with context from your docs and the user's workspace
- Support deflection — resolve common tickets from documentation and account state
- Onboarding — guide new users through setup with step-aware assistance
- Analytics Q&A — turn warehouse queries into plain-language answers
A reference architecture for SaaS agents
A copilot agent retrieves from tenant-scoped content and calls your product APIs through tools to read state and prepare actions. Users confirm anything that changes their data; tenant boundaries are enforced by keys and collections.
- Tenant-scoped keys and retrieval collections
- Tools into product APIs and warehouse
- Confirmation step for state-changing actions
- Usage analytics per tenant
Data governance and human oversight
Multi-tenancy is a security boundary. Ensure every request is scoped to a tenant, never mix collections, and log calls so you can demonstrate isolation to customers during reviews.
- Tenant-scoped keys and collections
- Per-tenant logs and usage attribution
- Confirmation before writes
- Data minimisation in prompts
From pilot to production
Pilot the copilot on internal accounts, then a design-partner tenant. Track deflection and task completion before a general release.
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 |
| Tenant isolation | Keys plus collections per tenant | Varies | You build it |
| Pricing predictability | Flat monthly self-serve plans | Often per-token | Your infra cost |
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.
How do we keep tenants isolated?
Use separate keys and retrieval collections per tenant, and log requests so isolation is verifiable in security reviews.
Can we bring our own cloud or keys?
Enterprise options include VPC deployment and bring-your-own-key arrangements; check the docs and enterprise page for current details.
Is per-token billing a risk?
Self-serve plans are flat monthly with fair-use usage and no per-token charges; see the live pricing page for current plans.