Chat & Reasoning Model · OpenAI

GPT-6 Luna

GPT-6 Luna is OpenAI's efficient GPT-6 model for focused, high-volume work. It accepts text and image input, has a 1,050,000-token context window and 128,000 max output tokens, and is available through both Codex and the OpenAI API.

At a glance (verified 2026-09-23)

Vendor
OpenAI
Type
Chat & Reasoning Model
Context window
1.05M tokens
Pricing
Short: $0.10 in / $0.01 cache hits / $0.125 cache writes / $0.50 out. Long (>272K input): $0.20 in / $0.02 cache hits / $0.25 cache writes / $0.75 out per 1M tokens.

Best for

Summaries and extractionFocused codingHigh-volume work

How to use GPT-6 Luna in TeamDay

Choose GPT-6 Luna in Teamday's Codex model picker. It works with a connected ChatGPT account or an OpenAI API key.

Frequently asked questions

How much does GPT-6 Luna cost?

Standard short-context API rates per 1M tokens are $0.10 input, $0.01 cache hits, $0.125 cache writes, and $0.50 output. Above 272K input tokens, the full request uses $0.20 / $0.02 / $0.25 / $0.75 rates.

Can I use GPT-6 Luna with an API key?

Yes. OpenAI lists gpt-6-luna for Responses and Chat Completions API requests, and Teamday offers it through Codex with an OpenAI API key.

What reasoning effort does GPT-6 Luna support?

Teamday's Codex picker offers low through max. OpenAI's API also supports none for direct requests.

Related

GPT-6 Lunais one of the models TeamDay's AI employees already run — no API keys, no infrastructure.

Hire your first AI employee →