Hosted Laya API
Laya is open weights, so you can always run it yourself. A hosted API makes sense when you do not want to run and patch a model server, when your traffic is small or spiky, or when you want to compare Laya with other decision models before committing. This page lists the options and what to check.
419 projects
laya-api
Lucasborges198
A Flask API uses Laya to classify business email messages into predefined intents
email-decider
Lucasborges198
Provides a Go HTTP gateway that forwards email intent decisions to a Laya-powered Python service
@wexare/laya-web
sarozarena
Runs the Laya typed-decision model in browsers using ONNX Runtime Web
poi-laya-judge
gokul0303
Provides a Gradio API for Laya-based semantic classification of points-of-interest search terms
laya-systemone-static
afelin
Hosts a static placeholder for a planned Laya system-one API while awaiting compute access
laya-systemone
afelin
Provides a Docker Space for recording requests to the finfin Laya system-one endpoint
nika-laya
nika-111155
Serves Laya decisions through a Jev-compatible API for Codename Nika
LayaPL
pleveneur
Runs locally converted Laya ONNX models from Node.js using ONNX Runtime
laya-server
sgaunet
Packages upstream Laya in a multi-architecture Docker image with CPU PyTorch
Laya-Playground
Emil-Wilson1
Provides a FastAPI playground for making typed decisions with Laya
laya-gateway
amanjoshi2002
Uses Laya to classify prompt safety and route prompts to suitable models
laya-article-examples
huaigu
Demonstrates Laya-based ticket triage, business gating, API serving, benchmarking, and data auditing
laya-node-client
felipenmoura
Provides a Node.js HTTP client for applications using a running Laya inference server
laya-system-one-docker
PikkonMG
Builds CPU and NVIDIA Docker images for the Laya System 1 server
gutcheck
sgaunet
A Go client for typed-decision APIs compatible with Jev and self-hosted Laya
loura-ticket-service
KhalidAlnujaidi
An asynchronous support-ticket classification service using a local Laya model
laya-local
ignit-fury
Serves the Laya decision model locally through a FastAPI classification API
laya-runpod
MelloB1989
Packages the Laya decision engine as a scalable RunPod serverless queue worker
LayaTool
naasking
Lets OpenWebUI users submit structured text decisions to a Laya model server
Laya-model-router
MikkelCardon
Routes prompts to Claude models by task type using Laya classification
laya-mlx-http
mjrussell91
Serves the Laya MLX question-answering model through a local FastAPI endpoint
warden-laya-service
tanishqsharmaa
Serves Laya typed-decision inference through gRPC and HTTP APIs for routing and reranking
laya-trt-serve
nmcglo
Exports Laya to TensorRT and serves it through a Jev-compatible API
zeabur-laya-service
Edwardlee-AI
Deploys Laya as a long-running HTTP decision service on Zeabur
Disclosure: layahost is run by the same team as laya.tools. It is listed first for that reason, not as a ranking.
Self-host or hosted?
Self-hosting is the better fit when text must not leave your machines, when volume is high and steady so that your own hardware is cheapest per call, or when you need on-device latency. The API servers page covers laya-serve, ollaya, Docker and native servers, and the run-locally guide covers Python, Mac, Node.js and CPU setups.
Check the hardware first. laya-cpu-benchmark concluded that a realistic CPU call is 0.3 to 2 seconds, and the Railway template reports about 0.2 to 0.9 s per call on CPU, with around 3.4 GB of memory for both checkpoints. Without a GPU or an Apple Silicon Mac, a self-hosted server can be slower than a hosted one.
A hosted API is the better fit when you do not want to operate a model server, when traffic is low or bursty, or when you want features around the model, such as templates, test sets or other models on the same endpoint.
Hosted options
Details are from each service's site, checked on 2026-10-14. Neither is affiliated with Convai Innovations or TypeSafe.
layahost
- Models: Laya (
laya-english,laya-multilingual) on its own servers in Helsinki. Cloudflare's open Clef and Clef-flash on the same API, answered on Cloudflare's Workers AI GPUs. - API: the Jev-compatible
POST /v1/systemone, and a simpler/v1/decidewith ready templates: moderation, spam, support_intent, routing, sentiment, priority, prompt_injection, pii and language. - Tools: test sets in the console to compare models on your own labelled data, decision flows built in a visual editor, an MCP server, an n8n node (
n8n-nodes-layahost) and a drop-in for Google's Perspective API. - Pricing: Laya per decision (one answered question), the same whatever the text length. Clef per input token. New accounts get $1 of credit after email verification, with no card.
- layahost.com · migrating from Jev
Laya Studio
- Models: Laya's English and multilingual checkpoints, routed automatically.
- Location: GPUs in Switzerland and an account database in Zurich. A Swiss-only mode keeps requests from failing over abroad. The site says request content is not stored and request metadata is kept for 30 days.
- API:
POST /v1/systemoneatapi.laya.studio. - Pricing: per input token, like Jev. New workspaces start with 6k free tokens.
- laya.studio
Railway template
The Railway template is a middle way: a one-click deploy of a Jev-compatible Laya server into your own Railway account. You pay Railway for the machine and your text goes only to your own service, but running and updating it is still your job. Its page says a Hobby or Pro plan is needed for the memory.
What to check
- Data location. Where the model runs, where accounts are stored, whether request text is kept, and whether a failover can move a request to another country. On layahost, Laya and Clef run in different places.
- Pricing model. Per-decision pricing does not depend on text length, so a long email costs the same as a short one, but three questions in one request count as three decisions. Per-token pricing, which Jev also uses, grows with the length of the text. Price both with your real message length and questions per request.
- Jev compatibility. Both hosted services accept
/v1/systemoneand say an existing Jev client works after a base-URL and key change (layahost documents this for the official TypeSafe SDKs). The answers still come from Laya, so a confidence threshold tuned on Jev does not transfer. See the differences on the API servers page. - Latency. The network adds to the model's own time. Laya Studio reports about 120 ms end to end from Europe for a warm request, and layahost lists about 0.1 s for Laya and 0.4 to 1 s for the Clef models. Measure from your own region.
- Accuracy. Hosting does not change the model. Independent benchmarks put base Laya behind Jev and the larger open alternatives on hard tasks (see the benchmark section there, and Laya benchmarks for the model card's own numbers). Run a few hundred of your own labelled examples before you move production traffic.
More ways to use Laya