Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions; drop-in base URL change |
| Models | 30+ models behind one API; open-weight options for private deployment |
| Typical patterns | Drafting support, tagging, archive search, localization |
| Integration path | Connects to CMS, DAM and archive systems through middleware |
| Pricing model | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing — see the live pricing page |
| Free tier | plugsky-micro and plugsky-lite on the free plan, no card required |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Live endpoints | Chat, streaming, JSON mode, function calling, embeddings, RAG and agents |
TL;DR
- Use the API behind the byline; humans verify and publish.
- Require citations from primary sources for every claim.
- Log model and prompt usage for rights and corrections.
- Plan text-first: audio transcription is still coming soon.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pick an internal workflow such as research synthesis or archive tagging.
- Build retrieval over your archive and approved source documents.
- Log model, prompt and editor for every assisted asset.
- Build against the OpenAI-compatible endpoint with scoped keys.
- Require fact-check and editor sign-off before publication.
- Add audio workflows when transcription endpoints become available.
Try it yourself
Open the LLM token calculator →
Where an AI API fits in media
Newsrooms and publishers need speed with accountability. The API helps most behind the byline, not on it:
- Research synthesis: condense filings, reports and transcripts into referenced briefings for reporters.
- Draft outlines: structure articles and scripts from notes for the journalist to write.
- Metadata and tagging: classify archive assets by topic, person and place for search and rights.
- Archive search: find prior coverage and source documents with citations.
- Localization: draft translations of text stories for in-market editors.
Security, privacy and data handling
Editorial integrity and rights are the constraints, and both need records:
- Keep a human in every publication decision; models assist, journalists verify.
- Log usage so rights and licensing questions can be answered.
- Protect source material and personal data from unnecessary exposure.
- Verify names, numbers and quotes against primary sources every time.
Deployment options and model choice
Source material and archives often warrant private deployment; public-facing production tools can run in a pinned region. Deployment is a choice among four tiers on the same OpenAI-compatible API: shared cloud, a private endpoint in your VPC, on-prem and air-gapped, with region selection for residency. The catalogue holds 30+ models behind one key, with open-weight models for disconnected sites, and switching provider is a base URL change. Live today: chat, streaming, JSON mode, function calling, embeddings, RAG and agents. Still coming soon: audio, images, moderation, files, batch, fine-tuning, assistants and the responses API. Start on the free plan with plugsky-micro and plugsky-lite, no card, or use the 14-day full-access trial for paid tiers; the live pricing page has current plans.
From pilot to production
The reputational risks in media are severe. Avoid:
- Publishing generated text without fact-checking and editor sign-off.
- Relying on model recall instead of retrieved primary sources.
- No record of which model and prompt produced an asset.
- Assuming transcription or moderation endpoints are live when they are coming soon.
- Tagging archive assets without a rights-review path.
Start with internal research and tagging, require citations for every claim, and keep an audit trail linking assets to prompts and editors. Add audio workflows only when the transcription endpoints ship.
Honest comparison
| Capability | Plugsky | Typical per-token API | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible chat, embeddings and tools | Usually compatible | Full rewrite |
| Deployment | Cloud, VPC, on-prem and air-gapped | Mostly cloud-only | You operate GPUs and serving |
| Data residency | Region selection and sovereign options | Limited regions | You control fully |
| Pricing | Flat monthly self-serve, fair-use usage | Per-token, harder to forecast | GPU plus operations cost |
| Model choice | 30+ models behind one API | Varies by provider | You host every model |
| Industry fit | Drafting support, tagging, archive search, localization | Generic API, you adapt it | You build every workflow |
Frequently asked questions
Can we keep our existing OpenAI SDK code?
Yes. Plugsky exposes an OpenAI-compatible API, so you change the base URL and model name and keep your integration.
Is there a free plan?
Yes. The free plan includes two free models, plugsky-micro and plugsky-lite, and does not require a credit card.
Can it transcribe interviews?
Not yet. Audio endpoints are coming soon. Use text transcripts from your existing tools with the chat endpoint until transcription ships.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover residency and SLA terms. See the live pricing page for current plans.
Will it replace journalists?
No. It reduces research and tagging overhead; editorial judgement, verification and accountability stay with people.
Which endpoints are live today?
Chat completions, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon.
Can we keep source material private?
Yes. Use private or region-locked deployment for sensitive material, and minimise what enters prompts.