Feature × Audience

How do MSPs build vision AI with Plugsky's architecture?

Vision for MSPs is a service you can sell: document and image understanding with tenant isolation built in. Plugsky runs image understanding on the OpenAI-compatible chat completions endpoint, and the same workspace, scoped-key, quota and audit model you use for text keeps each client's images separate, measured and reportable.

Key facts

Vision inputImage understanding runs on the OpenAI-compatible chat completions endpoint with supported multimodal models
Example modelplugsky-gemma-4 handles text plus image inputs such as screenshots, forms and product photos
Model access30+ models from efficient to frontier tiers behind one key
Dedicated media endpointsImage generation and editing endpoints are labelled coming soon
DeploymentHosted, VPC, on-prem and air-gapped options on Enterprise
Data handlingData encrypted at rest and in transit; API data is not used to train models
AuditPer-request logs with model, tokens, latency and user; SIEM export; retention up to 7 years
Free planplugsky-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

  1. Pick a repeatable workflow: invoice, form or ID document extraction.
  2. Define the output schema and the turnaround you will commit to.
  3. Set up per-client workspace, scoped key and quotas before the first file.
  4. Extract fields with JSON mode and route exceptions to a review queue.
  5. Report usage and audit evidence per tenant each month.
  6. Offer private deployment for clients with stricter data rules.
  7. Reuse the same onboarding checklist for every new client.
1Pick a repeatableworkflow: invoice,form or ID document2Define the outputschema and theturnaround you will3Set up per-clientworkspace, scopedkey and quotas4Extract fields withJSON mode and routeexceptions to a5Report usage andaudit evidence pertenant each month.6Offer privatedeployment forclients with

Original data

plugsky-gemma-Example model30+ models froModel accessPer-request loAuditplugsky-micro Free planSource: Plugsky facts table · updated 2026-09-26

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

CapabilityPlugskyVision-only API vendorBuilding in-house
Image understandingLive on supported multimodal chat modelsUsually the core productYou host and serve vision models
Image generationLabelled coming soonOften available todayCustom deployment work
API shapeOpenAI-compatible chat completionsVendor-specific SDKYou standardise it yourself
Model choice30+ models behind one keyNarrower catalogueOne model per integration
DeploymentHosted, VPC, on-prem and air-gappedUsually hosted onlyYour infrastructure only
ControlsRegion pinning, BYOK, per-request audit logs, SIEM exportVaries by vendorYou 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.