launchables°

Get started

Introduction

Myles decision models and the Decision API, in one page.

CheckingAsking api.launchables.ai

Myles models answer the small decisions inside a product or service: is this a scam, which team should take this, is this answer supported by its source. You send a state (the situation) and one or more questions. Each answer comes back with a calibrated probability for every option, read in a single forward pass, so your code decides what to automate and what to hand to a person. Myles models decide; they do not write text.

Quick startYour first decision in one request. Question typesnoul, choice and score, with examples. API referenceEvery field of POST /v1/decide. Model librarySix models, from a browser to one GPU.

Two ways to call a model

Myles-G: over HTTPPOST /v1/decide with a state and typed questions. Hosted or on your own GPU. CPU models: in your programdecide(state, question, options) on your own CPU. No key, no network.

Ways to run Myles

Hosted APIMyles-G 12B and Myles-G 31B on our endpoints: £0.0015 per million input tokens, output free. On your own hardwareServers, laptops and GPUs you operate, including disconnected networks. In your browserMyles-22M on your own device, no key needed. Code samplesPython, JavaScript and curl, ready to copy.

How a decision works

  1. Describe the situation. A message, a record, a policy and a case: text or JSON.
  2. Ask typed questions. Yes or no (noul), one of several labels (choice) or a level on a scale (score).
  3. Read the probabilities. Every option gets one. Automate what clears your threshold and send the rest to a person.

Myles-G runs behind the same API on our hosted endpoint and on your own hardware, so code written against one works on the other. The CPU models take the same three things (a state, a question and options) through a function call instead; see Model types.