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 | Claims summaries, policy Q&A, submission intake, broker support |
| Integration path | Connects to claims, policy and broker systems through controlled 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 |
| Identity and audit | SSO/SCIM, role-based access, SIEM audit log export and BYOK via KMS or HSM |
TL;DR
- Use the API to read and draft; keep decisions with adjusters and underwriters.
- Ground coverage answers in policy wording with citations.
- Test on historical cases, not just clean documents.
- Retain prompts, outputs and sources for audit and complaints.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pick one workflow, such as claims summarisation or submission intake.
- Assemble a historical test set with known outcomes and messy documents.
- Ground policy answers with RAG over current wordings and endorsements.
- Build against the OpenAI-compatible endpoint with per-workflow keys.
- Choose deployment and residency per data classification.
- Measure accuracy and adjuster time, keep human decisions, then expand.
Try it yourself
Open the function calling tester →
Where an AI API fits in insurance
Insurance is a document industry with regulated decisions. The API should shorten reading and drafting time, not decide:
- Claims document summaries: condense medical reports, repair estimates and correspondence into a timeline for the adjuster.
- Policy Q&A: answer coverage questions from the actual policy wording, with citations to clauses.
- Submission intake: extract risk details from broker submissions into structured fields for underwriters.
- Broker support: draft replies to common queries from approved product and process content.
- Regulatory correspondence: summarise regulatory notices into obligations and owners.
Security, privacy and data handling
Insurance decisions affect people's finances, so fairness, explainability and records are part of the design:
- Keep claims, coverage and pricing decisions with authorised humans.
- Test summaries and extractions for accuracy across the case mix, not just the easy cases.
- Restrict keys and data access per workflow and role.
- Retain prompts, outputs and cited sources for audit and complaint handling.
Deployment options and model choice
Insurers commonly pin a region for policyholder data and move claims-heavy workloads to a private deployment. Plugsky exposes the same OpenAI-compatible endpoint whether the workload runs in shared cloud, your VPC, on-prem or air-gapped, and region-locked planes keep processing where your policy requires. Teams route to 30+ models through one API, with open-weight options when a site has no external connectivity, and port code with a base URL change. Chat, 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. plugsky-micro and plugsky-lite are free with no card, a 14-day full-access trial covers paid tiers, and the live pricing page lists current plans.
From pilot to production
Claims and underwriting are scrutinised after the fact. Avoid:
- Letting extraction errors flow into payment calculations unchecked.
- Quoting coverage from model memory rather than policy wording.
- One key shared across claims, underwriting and marketing workflows.
- No record of which document revision an answer relied on.
- Testing only on clean, digital submissions.
Pilot on historical claims with known outcomes, measure extraction accuracy and adjuster time, and keep the decision with the adjuster. Retain citations so every assisted output can be reconstructed.
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 | Claims summaries, policy Q&A, submission intake, broker support | 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 the model decide claims?
No. It can summarise and draft; authorised staff must make coverage and payment decisions.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover residency, capacity and SLA terms. See the live pricing page for current plans.
Can policyholder data stay in our region?
Yes. Region-locked planes keep processing in a selected region, with VPC, on-prem and air-gapped options for enterprise setups.
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.
Would our data be used for training?
Plugsky processes customer data to provide the service; training exclusion belongs in your DPA. Confirm current terms with the enterprise team.