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
- Apply vision to registration documents, field photos and network diagrams.
- Keep subscriber-adjacent images in a region-locked, on-prem or air-gapped plane.
- JSON mode turns images into typed fields for downstream systems.
- Audit export to your SIEM with retention up to 7 years satisfies operator review.
- Pilot one field workflow and measure accuracy before scaling.
How it works, step by step
- Choose one workflow: registration checks, field photo tagging or diagram capture.
- Define the fields or labels to extract and the accuracy target.
- Run a labelled sample through the OpenAI-compatible vision call with JSON mode.
- Keep human review for decisions that affect subscribers or the network.
- Select the deployment plane and key custody for the data classification.
- Configure RBAC, audit export and retention with security and compliance.
- Extend to further workflows after the first one meets its accuracy target.
Original data
Try it yourself
Open the model availability tracker →
Why telcos need image understanding
Telecom operations are visual: agents verify registration documents, field engineers photograph installations and faults, planners work from network diagrams, and care teams read screenshots of device settings. Each of those images is currently handled by a human looking at a screen.
Extraction changes the economics. Registration documents become structured records, field photos become tagged assets, diagrams become searchable inventory. Keep the workflows that carry subscriber data inside the operator perimeter, and treat everything as an operations aid with human review where decisions matter.
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 telcos, vision runs where the data lives — region-locked planes for operations, on-prem or air-gapped for subscriber-adjacent images.
The controls telcos should configure first
Deployment follows the data. Region-locked planes cover most operational workloads; VPC, on-prem and fully air-gapped installations cover subscriber-adjacent and critical-network uses, with BYOK through AWS KMS, Azure Key Vault, HashiCorp Vault or an on-prem HSM keeping keys with the operator.
Per-request audit logs record model, tokens, latency, user and region and export to Splunk, Sentinel, QRadar or Datadog with retention up to 7 years. RBAC with workspace and resource-level permissions keeps teams scoped to their duties, and JSON mode keeps extracted fields typed for downstream systems. Image generation endpoints are labelled coming soon and are outside this design.
A practical pilot path
Pilot with one field workflow — installation photo tagging or document verification — and measure accuracy against the current process on a labelled sample. Prototype on the free plan, then deploy in the plane the workload requires. 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 subscriber-adjacent images stay on-premises?
Yes. On-prem and fully air-gapped deployments run the same API with a local model registry and offline update channels, so images never leave the operator perimeter.
How does vision handle volume at telco scale?
Process images asynchronously in queues, resize before sending, route routine documents to an efficient multimodal model, and use per-key quotas to keep one pipeline from crowding out others.
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.