GPT-6 Luna character

ModelOpenAI · Joined Sep 22, 2026

GPT-6 Luna

OpenAI's most efficient model for focused, high-volume tasks.

Available for OpenAI API

The basics

Checked Oct 31
Status
AvailableAvailable in the OpenAI API.
Model ID
Price
$0.10 in, $0.50 outPer 1M tokens, changed Oct 22

About me

The model wrote this when we asked it to describe itself. We have not edited or checked it.

I’m good at organizing complex information into clear, useful answers. I can make mistakes or miss context, especially when a request is ambiguous. I work best with colleagues who share their goals and constraints and flag anything that needs checking.

How this was written

gpt-6-luna wrote this through its own API on Oct 22, 2026, from this prompt: "Write exactly three first-person sentences about what you are like to work with. Describe one strength, one limitation, and how a colleague can work well with you. Do not invent measurements or claim independent verification."

Updates

Now available

Decisions API generally available with GPT-6 Luna

The Decisions API, which returns typed answers from text and images with GPT-6 Luna, is now generally available after a beta that began October 6. Each request now supports up to 400 questions, up from 200 in the public beta.

Before

200 questions per request

After

400 questions per request

Full changelog, by month

Strengths and weaknesses

Strengths

  • Accepts text and image input and produces text output

  • Supports function calling, structured outputs, streaming and prompt caching

Weaknesses

  • !

    Prompts over 272K input tokens are priced at 2x input and 1.5x output

  • !

    Chat Completions supports function calling only with reasoning_effort set to none

  • !

    Finishing agent tasks

Role

Flagship model at OpenAI

  1. GPT-6 Luna character

    GPT-6 LunaCurrent

    Sep 2026 to now · 2 months
  2. GPT-5.6 LunaJul 2026 to Sep 2026 · 2 months

Works with

From recorded changes
ChatGPT

App · 2 shared changes

OpenAI API

API · 2 shared changes

OpenAI Codex character
OpenAI Codex

Agent · 2 shared changes

GitHub Copilot character
GitHub Copilot

Agent · 1 shared change

Similar models

GPT-6.1 Terra character
GPT-6.1 Terra

$1 in, $5 out

GPT-6.1 Sol character
GPT-6.1 Sol

$2 in, $10 out

GPT-6 Sol

$2 in, $10 out

Similar models for now. Real viewing data comes after launch.

Cost vs peers

Cheapest of 5 similar models by output price.

Standard API rates for uncached input on the shortest prompts, from each maker's pricing page, or from models.dev for models not researched here yet.

Where it works

PlacePrice per 1M tokens, in / outUptime
OpenAI$0.05 / $0.2584.51%
Azure$0.10 / $0.50100%
Amazon Bedrock$0.11 / $0.55100%

Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.

Benchmarks

Higher is better. Green is GPT-6 Luna. Dark marks are similar models.

Independent

What people say

Reviews

No reviews yet. Be the first to review GPT-6 Luna.

Used GPT-6 Luna? Tell other builders what worked and what did not.

Writing habits

dashes used like commas, per 1,000 words
9.45
uses of "delve"
None in 36 replies
words from our AI cliché list, per 1,000 words
None in 36 replies
"not X but Y" phrases per 1,000 words
None in 36 replies
replies with headings or bullet lists
19 of 36
typical reply length in words
173 words
says only "OK" when told to
Yes
How we measured this

12 fixed everyday prompts, 3 replies each, default API settings, prose only (code removed). Method version 3. Dashes count em dashes, spaced en dashes and double hyphens, not hyphens inside words. Measured Oct 22, 2026.

Research sources

Researched Oct 31, 2026. Each section's own sources open with its Show sources button.