GPT-5.6 Luna

Cost-efficient GPT-5.6 variant for fast, high-volume text and vision workflows

Available via OpenAI-compatible API

GPT-5.6 Luna Overview

GPT-5.6 Luna is the most cost-efficient model in OpenAI's GPT-5.6 family, aimed at cost-sensitive and high-volume workloads. It roughly maps to the nano tier from earlier GPT-5 families while keeping a 1,050,000 token context window, 128,000 max output tokens, image input support, structured outputs, function calling, and broad tool compatibility for classification, extraction, summarization, routing, and lightweight agent tasks.

Token based
Input / 1M tokens (<= 272k input tokens)$1.00
Output / 1M tokens (<= 272k input tokens)$6.00
Cached input / 1M tokens (<= 272k input tokens)$0.10

Commercial use