Inference for faster, cheaper & smarter insurance agents
Balance claim surges and model oversight with one API for open and fine-tuned models, serverless and in your own cloud.
- GLM-OCR
- Qwen3 Reranker 4B
- GLiNER PII
- Your fine-tuned model
- GLM-5.3 Flash
- DeepSeek V4.1 Flash
- Gemma 4 31B
The leading insurance AI teams already run on open models
-
databricks.comApr 5, 2025
Introducing Meta’s Llama 4 on the Databricks Data + AI Platform
…process one million+ files daily… We exceeded our accuracy goals by fine-tuning Meta Llama… Prabhu Narsina, VP Data and AI, First American
-
predibase.comMar 12, 2025
Agentic AI at Scale: Marsh McLennan Saves 1M+ Hours
Fine-tuning not only ensured data sovereignty but also improved the accuracy of their fine-tuned Llama-3.1-8B-instruct model compared to GPT 3.5 and 4o-mini…
-
furtherai.comOct 21, 2026
Frontier Quality at a Fraction of the Cost: What We Found Testing GLM-5.3
We evaluated GLM-5.3 on two production insurance use cases… Our insurance workflows combine frontier and open-weight models to optimize for quality and cost…
-
bevaya.aiJan 22, 2026
GutenOCR: Our Approach to Grounded OCR for Production Workflows
…we built GutenOCR: a grounded OCR front-end created by fine-tuning Qwen2.5-VL (3B and 7B) into a single model that supports full-page reading, text detection, localized reading…
Keep up after the storm, not your provider’s rate limit
Each job runs on a model sized for it, next to your app. When a storm brings a surge of claims, you add GPUs to your own cluster instead of waiting on a provider’s quota.
Run a month of claims document work for 92% less
Task-sized open models do each job for a fraction of a frontier API’s price. Each line is priced from its task page, at an illustrative month’s volume.
- Read receipt and handwriting photos sent with claims
$4,000$250 More photos read right - Extract fields from claim forms and invoices
$5,604$636 More values exactly right - Rerank policy wording for each claim question
$12,500$744 Open model more accurate - Redact claimant data before an LLM reads it
$703$145 Less personal data exposed
Tuned on your task, an open model beats the frontier APIs at it
How each result was measured
- Contract-clause review
- LexGLUE UNFAIR-ToS: 3,882 Terms of Service clauses labelled by lawyers, none of them among the 5,532 the model was tuned on. F1 on the unfair class; each API at its best setting, with the lawyers’ annotation rulebook in its prompt.
- Possible fraud in bank messages
- BANKING77: 3,076 customer messages to a bank, 240 of them reporting a payment they don’t recognise or a card or phone lost, stolen or compromised, none among the 9,993 the model was tuned on. The share of those reports caught while 95% of the messages flagged are reports, each model’s threshold set on the scored messages; GPT-6 Luna at low effort.
- Business questions to chart specs
- Superlinked’s gd-1, August 2026: Gemma 4 31B tuned on generated questions, then scored once on a BI assistant’s 875-question benchmark, counting the answers that return the reference data. GPT-5.6 Sol at maximum reasoning was the strongest API. The training questions came from the benchmark’s own generator, which is the home advantage tuning on your own task gives.
Meet the AI oversight requirements of your insurance customers
| What the rule asks | SIE Serverless | SIE in your cloud |
|---|---|---|
Give insurers audit rights over AI vendors NAIC AI Model Bulletin, Dec 2023An insurer’s AI program should address, “Where appropriate and available, the inclusion of terms in contracts with third parties that: a) Provide audit rights and/or entitle the Insurer to receive audit reports by qualified auditing entities.” | SOC 2 Type 2 report Superlinked shares it under NDA | Audit it yourself The engine and open weights run in your account |
Explain every adverse underwriting decision NYDFS Circular Letter 7, Jul 2024“An insurer may not rely on the proprietary nature of a third-party vendor’s algorithmic processes to justify the lack of specificity related to an adverse underwriting or pricing action.” | Open weights No proprietary model between you and the answer | Re-run any decision You pin the exact model version |
Name where your data is processed EU DORA, Article 30(2)(b)Every ICT contract must state “the locations, namely the regions or countries, where the contracted or subcontracted functions and ICT services are to be provided and where data is to be processed, including the storage location”. | US or EU region Requests stay in the region you choose | Inside your network Your cloud account, in your region |
Keep AI logs for at least six months EU AI Act, Article 26(6), from Dec 2027For life and health insurance pricing, deployers “shall keep the logs automatically generated by that high-risk AI system to the extent such logs are under their control, for a period appropriate to the intended purpose of the high-risk AI system, of at least six months”. | Log on your side Keep each request and response in your own store | Logs in your account Every log stays under your control |
Start on SIE Serverless, or run it under your control
SIE Serverless
We host the models; you call one API.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Self-host the same open-source engine
- SOC 2 Type 2, US or EU data residency
- Create an account to try Serverless
SIE Cluster
Kubernetes in your own cloud, backed by our engineers.
- Terraform modules for your cloud
- Apache-2.0, same engine as Serverless
- GPU workers scale to zero between jobs
- Separate worker pools for each tenant
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment. SIE Local
The open-source server on your own machine.
- Runs on your NVIDIA GPU
- One container, no cluster
- Process your data fully offline
- Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-default Start from your task or your industry
Search and RAG
Documents
Text and LLM apps
- Chat Open LLM, OpenAI-style API
- Coding agents Tool calls for your coding agent
- Structured output Schema-valid JSON
- Classify text Your labels, no training
- Yes/no decisions Automate workflow checks
- Route requests Cheap or strong LLM, per request
- Extract names and dates People, orgs, places
- Knowledge graph Entities and their relations
- Translate text English into many languages