Key facts
| Vision input | Image understanding runs on the OpenAI-compatible chat completions endpoint with supported multimodal models |
| Example model | plugsky-gemma-4 handles text plus image inputs such as screenshots, forms and product photos |
| Model access | 30+ models from efficient to frontier tiers behind one key |
| Dedicated media endpoints | Image generation and editing endpoints are labelled coming soon |
| Deployment | Hosted, VPC, on-prem and air-gapped options on Enterprise |
| Data handling | Data encrypted at rest and in transit; API data is not used to train models |
| Audit | Per-request logs with model, tokens, latency and user; SIEM export; retention up to 7 years |
| Free plan | plugsky-micro and plugsky-lite, no card; 14-day full-access trial |
TL;DR
- Sell document and image understanding as a measurable managed service.
- One workspace, scoped key and audit trail per client applies to images too.
- JSON mode puts extracted fields into your own schema.
- Flat monthly plans protect margin when client volume spikes.
- Keep service scope on understanding — image generation is coming soon.
How it works, step by step
- Pick a repeatable workflow: invoice, form or ID document extraction.
- Define the output schema and the turnaround you will commit to.
- Set up per-client workspace, scoped key and quotas before the first file.
- Extract fields with JSON mode and route exceptions to a review queue.
- Report usage and audit evidence per tenant each month.
- Offer private deployment for clients with stricter data rules.
- Reuse the same onboarding checklist for every new client.
Original data
Try it yourself
Open the best AI model selector →
Why MSPs need image understanding
Every client has images nobody wants to process: supplier invoices, signed forms, delivery notes, ID documents, site photos. Document understanding is a natural add-on to managed services, and it is measurable — turnaround time, fields extracted, exceptions raised.
The service is only sellable if tenancy is airtight. A client's invoice should never be readable through another client's integration, and usage should be reportable per account. Build on the same workspace, key and audit model you already use for text workloads rather than inventing a parallel stack for images.
How vision works on the Plugsky API
Image understanding does not need a new platform. Add the image to the message content of a standard chat completion, and the response arrives exactly like a text completion: streamable, validatable with JSON mode, and usable with function calling. plugsky-gemma-4 covers high-volume triage such as screenshots, forms and document images, while stronger models handle the hard cases. Because 30+ models sit behind one key, changing tier is a model-name change. For MSPs, the same call runs behind a tenant gateway, which keeps each client's images inside its own workspace and audit trail.
The controls MSPs should configure first
Per client: a workspace boundary, a scoped key held server-side, quotas that cap runaway batches, and audit logs filtered by tenant for the monthly report. Constrain output with JSON mode so extracted fields land in your own schema, and keep source images only as long as the workflow needs them.
For clients with stricter requirements, offer VPC, on-prem or air-gapped deployment with BYOK. Because self-serve plans are flat monthly with unlimited fair-use usage, document-processing margin does not evaporate when a client's volume spikes. Image generation endpoints are labelled coming soon, so keep the service scope on understanding, extraction and routing.
A practical pilot path
Package one workflow — invoice or form extraction — with a defined schema and turnaround. Pilot with one client, measure exception rates, then reuse the same checklist for every onboarding. Prototype on the free plan and standardise on a paid plan as clients grow. See the live pricing page for current plans.
Honest comparison
| Capability | Plugsky | Vision-only API vendor | Building in-house |
|---|---|---|---|
| Image understanding | Live on supported multimodal chat models | Usually the core product | You host and serve vision models |
| Image generation | Labelled coming soon | Often available today | Custom deployment work |
| API shape | OpenAI-compatible chat completions | Vendor-specific SDK | You standardise it yourself |
| Model choice | 30+ models behind one key | Narrower catalogue | One model per integration |
| Deployment | Hosted, VPC, on-prem and air-gapped | Usually hosted only | Your infrastructure only |
| Controls | Region pinning, BYOK, per-request audit logs, SIEM export | Varies by vendor | You build the pipeline |
Frequently asked questions
Can we white-label the document service?
Yes. Keep your brand and workflow on top and run extraction on Plugsky behind your gateway; each client still gets its own workspace, scoped key and audit trail.
How do we avoid cross-client exposure?
Isolation is structural: a workspace and key per client, server-side key custody and tenant-filtered audit logs. No tenant shares a credential or a query surface.
Do we have to change our application code?
No. Image understanding uses the same OpenAI-compatible chat completions endpoint, so your SDK, auth and error handling carry over; the message content simply includes an image.
Is there a free plan?
Yes — plugsky-micro and plugsky-lite with 2 API keys and no credit card. A 14-day full-access trial is also available.
How is pricing structured?
Self-serve plans are flat monthly with unlimited fair-use usage and no per-token charges or overage fees. See the live pricing page for current plans.
Is image generation available?
Not yet — image generation and editing endpoints are labelled coming soon. Image understanding is live today on supported multimodal chat models.