Skip to content
OpenAI

GPT-6 Luna

GPT-6 Luna is a large language model made by OpenAI, added to the catalog on 22 Sep 2026. It has a context window of 1,050,000 tokens and costs $0.10 per 1M input tokens and $0.50 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: chat, text classification and lightweight tool-using tasks.

Price checked ยท source: OpenRouter

What GPT-6 Luna is

OpenAI GPT-6 Luna is a model for text and multimodal tasks. It accepts text, images, and files, and produces text. Its listed capabilities include tools, structured outputs, response formats, and reasoning. The provider describes it as suited to high-volume and latency-sensitive workloads, including chat, classification, and lightweight agentic tasks.

The model has a context length of 1,050,000 tokens and a maximum output of 128,000 tokens. The context capacity allows it to take in large amounts of material in a request, while the output limit supports generating lengthy text when a task calls for it. These limits may be relevant for work involving long documents or extended inputs, as well as tasks that need a substantial text response.

GPT-6 Luna may fit workflows that combine conversational text tasks with classification or lightweight tool-using processes. Its image and file inputs also make it an option for requests that include those materials alongside text. Structured outputs and response-format support are relevant when a result needs to follow a defined format. The listed capabilities describe what the model supports; the actual output depends on the request and the material provided. The catalog does not specify additional modalities beyond text, image, and file input, with text output.

Key features

  • Accepts text, image, and file inputs
  • Produces text
  • Has a 1,050,000-token context length
  • Supports up to 128,000 output tokens
  • Supports tools, structured outputs, response formats, and reasoning

Typical uses

  • Chat
  • Text classification
  • Lightweight tool-using tasks
  • Working with long documents
  • Generating structured text

GPT-6 Luna pricing

US dollars, list price through OpenRouter.

Checked
GPT-6 Luna price list, by variant
ItemStandardBatch
Input, per 1M tokens$0.10$0.05
Output, per 1M tokens$0.50$0.25
Cached input read, per 1M tokens$0.01$0.005
Cache write, per 1M tokens$0.125$0.0625
Web search, per search$0.01$0.01
Input above 272,000 prompt tokens, per 1M$0.20$0.10
Output above 272,000 prompt tokens, per 1M$0.75$0.375
Variants of GPT-6 Luna that share this page
VariantModel id
Batchopenai/gpt-6-luna:batch

A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.

No price change since it was added on 22 Sep 2026.

What typical tasks cost with GPT-6 Luna
What a task costsCost
Answer a short question500 in / 300 out$0.0002
Summarise a 50-page PDF25,000 in / 800 out$0.0029
Review a 2,000-line source file30,000 in / 2,000 out$0.0040
Read a 300-page contract set150,000 in / 1,500 out$0.016
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

GPT-6 Luna specifications

GPT-6 Luna limits and identity
Model idopenai/gpt-6-luna
Versiongpt-6-luna-20260922
Context window1,050,000 tokensAbout 787,500 English words
Max output128,000 tokens
Knowledge cutoffNot published
Added to catalog22 Sep 2026
GPT-6 Luna capabilities
Input typesfile, image, text
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlYes
Content moderationApplied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

No output has been recorded for GPT-6 Luna yet.

GPT-6 Luna questions

How much does GPT-6 Luna cost?

GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0029.

What is the context window of GPT-6 Luna?

1,050,000 tokens, or roughly 787,500 English words. It can write up to 128,000 tokens in one response.

Can GPT-6 Luna read images and PDFs?

It accepts text, images and files as input. It produces text, so it cannot generate images.

How do I try GPT-6 Luna?

Use the "Try GPT-6 Luna" button on this page. It opens the chat with GPT-6 Luna selected; you type the question and press send.

Try GPT-6 Luna on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.