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 |
| Coding models | Coding-focused models available in the catalogue |
| Read-only default | Repo-scoped access with no write actions |
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 agent access read-only across repositories.
- Pilot review summaries before docs Q&A.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot review summaries on an internal repository.
- 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.
- Keep merges and deploys outside agent scope.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Open the OpenAI-compatible API tester →
Where AI agents pay off in software companies
Software Companies 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.
- Review support — summarise diffs and flag risky patterns for reviewers
- Docs Q&A — answer internal questions from architecture and runbook content
- Ticket triage — classify bug reports and link likely components
- Release notes — draft changelogs from merged work for editing
A reference architecture for software companies agents
A review agent reads a diff and prior review comments to produce a checklist, while a docs agent retrieves from architecture notes and runbooks. Engineers approve and merge; the agent never pushes code or changes CI settings.
- Repo and docs retrieval collections
- Read-first tools into trackers and CI
- Diff-scoped prompts to control context
- Approval gates for any write action
Data governance and human oversight
Source code is your most sensitive IP. Keep retrieval inside your boundary, control which repositories an agent may read, and log access. Use the migration checker to confirm endpoint compatibility before moving workloads.
- Repo-scoped access control
- Audit logs for agent reads
- No autonomous merges or deploys
- Secrets excluded from context by policy
From pilot to production
Pilot review summaries on an internal repository, then docs Q&A. Track review time saved and false-positive rate before broadening.
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 |
| Code access | Repo-scoped, read-only by default | Varies | You enforce it |
| Deploys | Engineer-owned; agents never push | 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 it review our private code?
Yes, within the access you grant: scope retrieval and tools to approved repositories, and keep deployments inside your boundary where required.
Will it push commits?
No — keep write access out of scope. Agents summarise, draft and flag; engineers own changes.
Does it work with our existing SDK code?
Yes, the API is OpenAI-compatible: change the base URL and model name, then run your existing tests.