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 |
| Free prototyping | Free plan with plugsky-micro and plugsky-lite, no card |
| Portability | OpenAI-compatible API keeps your code portable |
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.
- Prototype free, then upgrade when usage is proven.
- Keep the first agent narrow and measured.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Ship one narrow agent and measure it for two weeks.
- 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.
- Prototype on free models before committing spend.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the private LLM cost estimator →
Where AI agents pay off in startups
Startups 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.
- Prototyping — ship agent features in days using the OpenAI-compatible API
- Support automation — deflect common questions from your docs
- Lead qualification — gather and route inbound interest
- Internal knowledge — answer ops and product questions for the team
A reference architecture for startups agents
A support agent retrieves from your help centre and escalates unknowns, while a qualification agent updates your CRM through tools. Keep the first version narrow, instrument everything, and expand only where the metrics hold.
- Start with one collection and one integration
- Tools into helpdesk and CRM
- Human review for anything customer-facing
- Usage and cost tracking per key
Data governance and human oversight
Early-stage risk is mostly about quality and data hygiene. Keep customer data minimal, scope keys per environment, and avoid sending anything unreviewed at scale until deflection quality is proven.
- Separate development and production keys
- Review before high-volume sends
- Keep customer data minimal
- Watch usage on your dashboard
From pilot to production
Build one useful agent, measure it for two weeks, then decide whether to expand or remove it. Free-plan models are enough for prototyping; move to a paid plan when usage grows.
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 |
| Time to prototype | Days with an OpenAI-compatible API | Varies | Weeks of infra work |
| Cost model | Flat self-serve with a free tier | 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.
What does the free plan include?
Two free AI models, plugsky-micro and plugsky-lite, with no credit card, which is enough to prototype and validate an agent.
How do we control costs as we grow?
Self-serve plans are flat monthly with fair-use usage; see the live pricing page for current tiers rather than estimating from token prices.
Can we migrate later?
Yes — the API is OpenAI-compatible, so moving between models or keeping your code portable is a base URL and model-name change.