StoryFirst seen
A structured, probability-scored way for apps to pick models and tools drew ecosystem support within hours, pointing toward routing as standard plumbing for multi-model products.
Everything it touches
8 names 3 voices 3 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
GPT-6 Luna Decisions is now on OpenRouter @OpenAI's Decisions API lets your app pick the right model, tool, or action. Send text, JSON, or images and get back typed answers with probabilities $0.10/M input, output is free, 1M contextRead original on X
I released an LLM plugin for sending prompts to OpenAI's new Jev-clone decision model that's based on GPT-6 LunaRead original on X
We launched support for OpenAI's new Decision API. It's similar in concept to jev from @typesafeai but multimodal. So ideal for finally building Hotdog or not Hotdog!Read original on X
OpenAI's Decisions API for routing AI tasks lands on OpenRouter
OpenAI's Decisions API for routing AI tasks lands on OpenRouter
OpenAI's Decisions API for routing AI tasks lands on OpenRouter
OpenAI's Decisions API for routing AI tasks lands on OpenRouter
OpenAI's Decisions API for routing AI tasks lands on OpenRouter
OpenAI's GPT-6 Luna Decisions API lands on OpenRouter
Shared connections
The Yang-Mills Working Group plans to publish OpenAI's submitted code and its validation, so the claim can be checked by mathematicians.
Disney plans to use the Adobe models in its studios and at its theme parks, tailored to its own properties.
It nearly matches the company's larger model at a fraction of the price, aimed at repeated, token-heavy tasks that AI agents run.
A chart from its blog suggests extra compute spent at answer time is not hitting diminishing returns.