Feature × Audience

How should enterprise architects plan multimodal AI with Plugsky?

Enterprise architects should split the multimodal stack by availability: vision in chat completions, embeddings and RAG are live and can be productionised now; image generation, audio transcription and speech are coming soon and belong on a roadmap, not in a launch. Design one internal model interface, pin inference per region, and govern binary content with the same rigour as text.

Key facts

Live capabilitiesVision input, embeddings and built-in RAG
Coming soonImage generation, audio transcription, speech and moderation endpoints
Request limit16 MB maximum request body; split large scans
Model access30+ models behind one OpenAI-compatible endpoint
ResidencyRegion pinning plus VPC, on-prem, air-gapped and BYOC topologies
ObservabilityModel, tokens, latency, status, key, project and region logged per request
GovernancePII modes, scoped keys, RBAC and SIEM-exportable audit events
SLA99.9% to 99.95% single-region, 99.99% multi-region deployments

TL;DR

  • Productionise vision, embeddings and RAG now; roadmap image and audio.
  • Design one internal multimodal interface so future endpoints are additive.
  • Treat images and scans as sensitive data with the same controls as text.
  • Pin inference by region and keep observability per request.
  • Ask vendors for endpoint status in writing before promising a capability.

How it works, step by step

  1. Produce a capability map separating live endpoints from coming-soon ones, and circulate it with product teams.
  2. Define one internal interface for model calls so modality changes are provider changes.
  3. Design data handling for binary inputs: redaction, retention, storage location and access control.
  4. Choose embedding and retrieval patterns per use case, with collections scoped to domains.
  5. Set residency and topology per workload before the first pilot, not after.
  6. Add routing and audit requirements to the platform standard so multimodal inherits them for free.
1Produce acapability mapseparating live2Define one internalinterface for modelcalls so modality3Design datahandling for binaryinputs: redaction,4Choose embeddingand retrievalpatterns per use5Set residency andtopology perworkload before the6Add routing andaudit requirementsto the platform

Original data

16 MB maximum Request limit30+ models behModel access99.9% to 99.95SLASource: Plugsky facts table · updated 2026-09-26

Try it yourself

Open the embedding model comparison →

A capability map: live versus roadmap

The most common multimodal architecture mistake is designing for parity with a vendor's marketing page. Today, Plugsky's live stack is vision in chat completions, embeddings and retrieval-augmented generation. Image generation, audio transcription, speech and moderation endpoints are coming soon.

Publish that distinction internally. It lets product teams build document understanding and semantic search immediately, while anything requiring generated imagery or voice stays behind a roadmap dependency — and it gives you a defensible answer when a stakeholder asks why a competitor's demo includes audio.

Data handling for binary content

Images, scans and audio are data with the same classification as the text they contain, often more. Extend your existing controls rather than inventing parallel ones: redaction before inference, project-scoped keys per environment, retention rules per corpus, and residency pinning for inference, embeddings and logs together.

  • Request size: the 16 MB body limit forces per-page splitting — a useful constraint because it keeps payloads reviewable.
  • Storage: where you store the original artefacts is your decision; keep it consistent with the region you pinned for inference.
  • PII modes: no-PII, detect-only and passthrough cover text prompts; pair them with container-level controls for binaries.

Integration roadmap and vendor risk

Architect for addition, not replacement. One internal interface that takes messages and returns completions can carry vision today and accept audio or image output later without touching product code. Keep feature flags around anything unshipped, and write endpoint status into your vendor risk register so a roadmap item cannot quietly become a launch dependency.

The platform already provides the surrounding governance: 30+ models behind one endpoint, region pinning, scoped keys, RBAC, audit export and SLAs from 99.9% up to 99.99% on multi-region deployments. Multimodal inherits all of it, which is the real argument for consolidating rather than adding a second vendor for vision alone.

Honest comparison

DimensionPlugskySingle-modality vendorsSelf-hosted multimodal
Live modalitiesVision, embeddings, RAGUsually oneWhatever you serve
Roadmap transparencyEndpoints labelled coming soon in docsVariesUnder your control
GovernanceScoped keys, RBAC, audit exportSeparate per vendorYou build it
ResidencyRegion pinning, VPC, on-prem, air-gappedLimited regionsWherever you deploy
Integration surfaceOne OpenAI-compatible endpointOne SDK per vendorCustom serving

Frequently asked questions

Which multimodal endpoints are production-ready?

Vision input in chat completions, the embeddings endpoint and built-in RAG are live. Image generation, audio and moderation endpoints are coming soon.

How do we avoid building on unshipped features?

Keep a written capability map, gate anything unshipped behind feature flags, and record endpoint status in your vendor risk register.

How should images and scans be governed?

Treat them as sensitive data: redact before inference, scope keys per environment, pin inference and logs to a region, and apply retention rules per corpus.

What is the request size limit?

Request bodies cap at 16 MB, so split multi-page documents into page-sized calls and reassemble in your application.

Which embedding setup should we standardise on?

Start with the platform's embedding model for semantic search and retrieval, and compare alternatives against your own corpus before standardising.

Can everything run in our own environment?

Yes. The same API runs in VPC, on-prem, air-gapped and bring-your-own-cloud topologies where data cannot leave your estate.

What governance comes with it?

Project-scoped keys, RBAC, PII modes, per-request logging exportable to SIEM, and SLAs from 99.9% to 99.99% depending on topology.