Industry Solutions

How should insurers use an AI API?

Insurers use an AI API for claims document summarisation, policy Q&A, submission intake, broker support and regulatory correspondence, with human adjusters keeping decision authority. Fairness, explainability and auditability are regulatory expectations, so log prompts and outcomes, restrict keys per workflow and test on historical cases. An OpenAI-compatible API with private deployment and a DPA keeps personal claims data within your governance boundary.

Key facts

API compatibilityOpenAI-compatible /v1/chat/completions; drop-in base URL change
Models30+ models behind one API; open-weight options for private deployment
Typical patternsClaims summaries, policy Q&A, submission intake, broker support
Integration pathConnects to claims, policy and broker systems through controlled middleware
Pricing modelFlat monthly self-serve plans with unlimited fair-use usage; no per-token billing — see the live pricing page
Free tierplugsky-micro and plugsky-lite on the free plan, no card required
DeploymentPlugsky cloud, your VPC, on-prem and air-gapped options
Identity and auditSSO/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

  1. Pick one workflow, such as claims summarisation or submission intake.
  2. Assemble a historical test set with known outcomes and messy documents.
  3. Ground policy answers with RAG over current wordings and endorsements.
  4. Build against the OpenAI-compatible endpoint with per-workflow keys.
  5. Choose deployment and residency per data classification.
  6. Measure accuracy and adjuster time, keep human decisions, then expand.
1Pick one workflow,such as claimssummarisation or2Assemble ahistorical test setwith known outcomes3Ground policyanswers with RAGover current4Build against theOpenAI-compatibleendpoint with5Choose deploymentand residency perdata6Measure accuracyand adjuster time,keep human

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

CapabilityPlugskyTypical per-token APIBuilding in-house
API compatibilityOpenAI-compatible chat, embeddings and toolsUsually compatibleFull rewrite
DeploymentCloud, VPC, on-prem and air-gappedMostly cloud-onlyYou operate GPUs and serving
Data residencyRegion selection and sovereign optionsLimited regionsYou control fully
PricingFlat monthly self-serve, fair-use usagePer-token, harder to forecastGPU plus operations cost
Model choice30+ models behind one APIVaries by providerYou host every model
Industry fitClaims summaries, policy Q&A, submission intake, broker supportGeneric API, you adapt itYou 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.