Overview
This is a self-hosted deployment of the Laya Decision Engine . It runs as a single GPU-powered EC2 instance allowing you to keep your data private and evaluate typed decisions with no per-token charges. Access is via HTTP on port 8080. Once the instance is powered on, the server requires up to 2 minutes to load the decision models before it is ready to serve requests. Highlights of the Laya model include:
-
Non-autoregressive System 1 engine: answers typed choice, score, and noul questions over text, email, tickets, or JSON in a single forward pass. It never generates text, so there is nothing to parse and nothing to hallucinate.
-
Built-in Router preloads the English, multilingual, and typed-decisions checkpoints and selects among them per request, covering 100+ languages. Measured latency on Tesla T4 is about 33 milliseconds for a single question.
-
Apache 2.0 open weights. Three checkpoints: English ModernBERT-large (421M), multilingual mmBERT-base (322M), and typed-decisions (421M).
-
Treat Laya as a fast foundation model to specialize. The published 0.766 typed-decisions score is from the fine-tuned checkpoint; base checkpoints score near 0.35 on that benchmark. Keep choice schemas under 20 options, or use a two-step hierarchy.
Example API calls
Replace PUBLIC_IP with the instance address.
Health check
curl http://PUBLIC_IP:8080/healthExpected response
{"status":"ok"}Predict (optional model field pins english, multilingual, or typed-decisions; omit it to let the Router choose)
curl -X POST http://PUBLIC_IP:8080/predict -H 'Content-Type: application/json' -d '{"state":{"body":"I was charged twice, please refund."},"questions":{"queue":{"type":"choice","instructions":"Which queue owns this ticket?","criteria":{"billing":"refunds, invoices","infrastructure":"outages","support":"general inquiries"}},"urgency":{"type":"score","instructions":"How urgent is this ticket?","criteria":["low","medium","high","critical"]},"churn_risk":{"type":"noul","instructions":"Does the customer threaten to cancel?"}}}'Expected response shape
{"routing":{"model":"english","reason":"English Latin text"},"answers":{"queue":{"type":"choice","choice":"billing","confidence":0.94},"urgency":{"type":"score","score":1.8},"churn_risk":{"type":"noul","noul":0.16,"confidence":0.84}}}Routing may select multilingual for non-English input. Pin a checkpoint with "model":"typed-decisions" in the JSON body.
Highlights
- Data security, privacy, and confidentiality
- Predictable cost
- Unlimited usage of a dedicated model
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
g4dn.xlarge Recommended | $0.09 |
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
Refunds may be considered on a per-case basis. Please contact us at support@salientengineering.com for inquiries.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Ubuntu security updates through 2026-11-17. The AWS kernel is 7.0.0-1017. On GPU images the matching NVIDIA open kernel module was installed in the same update, then linux and NVIDIA packages were held again so a later unattended upgrade cannot split the driver from the kernel. Application behavior is unchanged.
Additional details
Usage instructions
- Deploy the EC2 instance, configure the Security Group to only allow inbound port 22 and 8080 from your trusted IP address(es)
- After the instance is powered on, allow up to 2 minutes for Laya to load the decision models. GET /health returns 200 when ready.
- Access the Laya Decision Engine via FastAPI on port 8080. POST /predict accepts {state, questions} and optional model (english, multilingual, typed-decisions). GET /health reports readiness.
Test via HTTP with: curl -X POST http://<PUBLIC_IP>:8080/predict -H 'Content-Type: application/json' -d '{"state":{"body":"I was charged twice, please refund."},"questions":{"churn_risk":{"type":"noul","instructions":"Does the customer threaten to cancel?"}}}'
Resources
Vendor resources
Support
Vendor support
The Salient Engineering support team can be reached at: support@salientengineering.com
Our team is happy to assist with deployment and configuration issues.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.