Industry First

The world's first insurance-native language model

Reinsure-8B is a small language model built exclusively for the reinsurance and insurance industry. Fine-tuned from Llama 3.1 on reinsurance workflows, treaty structures, bordereaux formats, and London Market language.

Deploy it sovereign inside your own infrastructure, or call it as an inference API. Either way, you get a model that speaks insurance — without prompt engineering, without hallucinated policy terms.

£0.000005 / token · Billed monthly · No minimum
Model
Reinsure-8B
by Reinsured.AI
BaseLlama 3.1 8B
Params8 Billion
WeightsF16 / MLX
Size20.6 GB
DomainReinsurance
LicenseOpen weights
SovereignAPI
The Principle

What is Organisational Sovereign AI?

Sovereign AI means the model runs inside your control. Your weights, your infrastructure, your data. No dependency on a third-party API that can change pricing, deprecate versions, or inspect your query traffic.

For regulated insurance businesses — Lloyd's syndicates, global reinsurers, captives, MGAs — sovereignty is not a preference. It is a compliance requirement. Sensitive submissions, treaty terms, and client data cannot flow to shared cloud endpoints.

Reinsure-8B is purpose-sized for sovereign deployment. At 8 billion parameters, it runs efficiently on enterprise GPU hardware — a single A100 or equivalent — without the infrastructure overhead of 70B+ models. This is the practical path to production AI in a regulated industry.

01
No data egress
Your submissions, treaty data, and client information never leave your environment. Inference happens entirely within your perimeter.
02
No vendor lock-in
Open weights on HuggingFace. You can run, fork, modify, and fine-tune without permission. The model is yours.
03
No shared training
Your queries and outputs do not feed any shared training pipeline. Your competitive intelligence stays yours.
04
Audit-ready
Every inference is traceable within your own infrastructure. Full explainability for internal audit, regulator review, and Lloyd's oversight.
Deployment

Two ways to run Reinsure-8B

Sovereign
Recommended

Deploy the full model weights inside your own cloud or on-prem environment. Fine-tune it on your proprietary data. Complete data sovereignty and maximum performance.

Your weights, your infrastructure
Deploy Reinsure-8B inside your own cloud, on-prem, or private VPC. No data ever leaves your perimeter. Full model sovereignty — you own the weights, you control the runtime.
Fine-tune on your proprietary data
Bring your underwriting guidelines, treaty terms, bordereaux history, and cedant correspondence. Fine-tune Reinsure-8B on your specific corpus to create a model that knows your business at a level no generic LLM can match.
Regulatory safe by design
With the model running entirely within your environment, you satisfy data residency, GDPR, Solvency II, and Lloyd's data governance requirements without architectural workarounds.
Hardware: A100 80GB or equivalent
Deployment: Docker / Kubernetes / bare metal
Fine-tuning: LoRA / QLoRA supported
Inference API
Fast start

Call Reinsure-8B as a hosted API. No infrastructure required. Pay per inference token. Ideal for teams validating use cases or building lightweight integrations.

Live in minutes
Point your application at our inference endpoint. No infrastructure to manage, no GPU provisioning. Start extracting value from Reinsure-8B with a single API call.
Pay per token
Consumption-based pricing means you scale from proof-of-concept to production without upfront commitment. Ideal for teams validating use cases before a full sovereign deployment.
Insurance-tuned responses, out of the box
Even in API mode, Reinsure-8B returns answers grounded in insurance domain knowledge — correct terminology, accurate treaty logic, reinsurance-aware reasoning. No prompt engineering required.
// Inference API — OpenAI-compatible
const response = await fetch(
"https://reinsured.ai/api/v1/inference",
{
method: "POST",
headers: {
"X-API-Key": process.env.REINSURE_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "reinsure-8b",
messages: [{ role: "user", content: "Summarise this bordereaux..." }],
stream: true,
})
}
)
Domain Coverage

Built for the language of reinsurance

Generic large language models are trained on the open internet — predominantly consumer content, code, and general text. Insurance knowledge is sparse, often incorrect, and never updated with current market practice.

Reinsure-8B was fine-tuned on a curated corpus of reinsurance-specific content — treaty wordings, bordereaux templates, Lloyd's market standards, catastrophe model outputs, underwriting guidelines, and claims documentation.

The result is a model that interprets reinsurance language correctly by default, without requiring you to explain what a "binder", "burning cost", or "cedant" means in every prompt.

Supported use cases
Treaty structure analysis and interpretation
Bordereaux data extraction and validation
Facultative submission summarisation
Claims triangulation and IBNR language
Reinsurance contract clause extraction
Underwriting guideline compliance checking
Market filing and regulatory language parsing
CAT model narrative interpretation
Cedant reporting and reconciliation
London Market slip and MRC document parsing
Why not a generic LLM?

Domain-specific beats general-purpose

Applying a general-purpose model to insurance creates compounding problems — hallucination, data risk, poor economics. Reinsure-8B is purpose-built to eliminate each of them.

DimensionGeneric LLM (GPT, Claude, Gemini)Reinsure-8B
Domain knowledgeRequires extensive prompt engineering to produce insurance-accurate responsesTrained on reinsurance workflows and market language — correct by default
Data sovereigntyData sent to third-party endpoints; no guarantee of isolationFull sovereign deployment option — weights in your environment, zero data egress
Fine-tuningFine-tuning requires large data volumes and significant engineering effort8B parameter size is optimal for domain fine-tuning — fast, cost-effective, precise
Hallucination riskHigh risk on insurance-specific terms, treaty logic, and regulatory languageDomain pre-training reduces hallucination on insurance concepts by design
Deployment optionsAPI-only; sovereign deployment not viable for most enterprise teamsBoth modes: sovereign self-hosted or consumption-based inference API
Cost at scaleLarge model sizes mean high inference cost per token at production volumes8B parameters — high throughput, low cost per token, runs on modest GPU hardware
Architecture

The intelligence engine behind the stack

Reinsure-8B is the reasoning core that powers Reinsured.AI's Context Cloud and AI Agents. When an agent interprets a treaty clause, extracts a bordereaux field, or classifies a submission, it is calling on Reinsure-8B — a model that already understands the domain.

Organisations that deploy Reinsure-8B sovereign get the additional option to fine-tune it on their own internal data, creating a model layer unique to their underwriting philosophy and market positioning — one that becomes a proprietary asset over time.

View platform architecture
Our Spoke
System of Actions
Triggered by agent decisions powered by Reinsure-8B reasoning
Our Core
System of Decisions
AI agents use Reinsure-8B to interpret context and determine next steps
Differentiator
System of Context
Context Cloud uses Reinsure-8B to parse, classify, and enrich ingested data
Partner Systems
System of Record
Partner systems feed raw data — Reinsure-8B converts it to structured intelligence
Get Started

Ready to run an insurance-native model?

Talk to our team about a sovereign deployment scoped to your infrastructure, or create an account to start testing the Reinsure-8B inference API today.