Ask typed questions about any text or JSON and get calibrated answers in milliseconds. Private, open source, on your own hardware. Download Browse models Real output: routed to laya:en, answered in 8.9 ms on an RTX 4090.\n\nFast Drop-in compatible Open models Your data stays yours Platforms Fast Decisions in milliseconds.

A decision model answers in a single forward pass, with no token-by-token generation. On your own GPU, a five-question request to Laya takes about 10 ms, end to end through the HTTP API.\n\nDrop-in compatible Speaks Type Safe's API. Ollaya serves /v1/systemone and /v1/models with Type Safe's request and response shapes.

The official Type Safe Python SDK 0.7.1 works unchanged against a local server.\n\nOpen weights, ready to pull. Start with Laya from Convai Innovations: an English model, a 100+ language model, a model fine-tuned for typed decisions, and a router that picks for you. Private by default.

Runs where you work. Get up and running in minutes. One binary, one command: ollaya run laya.