Intel / post

OpenAI's Decisions API arrives on OpenRouter for fast typed routing calls

Source: x.com
Date: Published Oct 7, 2026

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 context https://t.co/MCwtEBqpIZ https://t.co/uzzhmkogD8

Oct 7, 2026 View on X

Context

OpenRouter, a service that gives developers one interface to many AI models, listed OpenAI's Decisions API as GPT-6 Luna Decisions. According to OpenRouter, the API from OpenAI lets an app pick the right model, tool or action. A developer sends text, JSON or an image and gets back typed answers with probabilities instead of a written reply, which a program can use directly.

The post lists a price of $0.10 per million input , free output and a 1M-token , meaning the amount of text a request can include. Because output is free, the listed cost covers only what is sent in. A related Intel item reports OpenAI's claim that the API is up to 10x faster than calling GPT-6 Luna through its Responses API. That figure is OpenAI's claim as reported there, and the OpenRouter post itself reports no speed or accuracy measurements.

Terms in this piece · Glossary

token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Read the source x.com