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 |
| Grounding | Retrieval over your brand, product and claims libraries |
| CMS tools | Function calling into your CMS and analytics stack |
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.
- Ground copy in a vetted claims library, not model memory.
- Humans publish; agents draft and check.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Start with briefs and clustering where quality is easy to judge.
- 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.
- Clean the claims library before enabling copy QA.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in marketing
Marketing 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.
- Content briefs — assemble audience, angle and evidence from approved sources
- SEO clustering — group queries into topics and map them to pages
- Brand and claims QA — flag copy that conflicts with your guidelines
- Performance summaries — turn analytics exports into plain-language recaps
A reference architecture for marketing agents
A brief agent retrieves product facts and past winners to draft an outline, while a QA agent checks copy against your claims library and flags risky phrasing. Editors review and publish through your CMS.
- Brand, product and claims retrieval collections
- Tools into CMS, analytics and project management
- Approval step before publishing
- Prompt templates for briefs, clusters and QA
Data governance and human oversight
Marketing runs on claims and third-party content, both of which need care. Ground generation in a vetted claims library, keep provenance links, and require human sign-off so no unverified statement ships.
- Approved claims library in retrieval
- Editorial approval before publication
- Audit log of generated drafts and edits
- Third-party licences documented
From pilot to production
Pilot briefs and SEO clustering first, where quality is easy to judge. Add claims QA once the library is clean; measure edit distance, not just output volume.
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 |
| Brand control | Retrieval plus editorial review | Varies | You build it |
| Publishing | Human-approved; CMS via tools | Varies | You integrate |
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.
Will content sound generic?
Only if you let it. Grounding generation in your brand and product collections, plus editorial review, keeps voice and specifics on target.
Can it publish directly?
Keep human approval in the flow at first; agents can call your CMS through tools, but publication should be a reviewed action.
Can it bring its own statistics?
It should not. Restrict outputs to your approved sources and treat any unsourced number as a defect.