GPT-6 Luna Pro
GPT-6 Luna Pro 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: analyzing long documents, interpreting images with text prompts and working through complex questions.
Price checked ยท source: OpenRouter
What GPT-6 Luna Pro is
OpenAI GPT-6 Luna Pro is a text-producing model from OpenAI, described as the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro. The provider describes this mode as intended for higher-quality responses on complex tasks. It accepts text, images, and files, and produces text. The listed context window is 1,050,000 tokens, with a maximum output of 128,000 tokens. This gives it room to work with large supplied inputs and produce long responses, within those listed limits.
Its supported capabilities include reasoning, tools, structured outputs, and response_format. These options make it suitable for tasks that benefit from problem solving, tool-assisted workflows, or responses constrained to a defined format. The facts do not specify particular tools, file types, image tasks, or output schemas, so those details depend on the setup using the model.
Potential applications include analyzing lengthy text or supplied files, interpreting image inputs alongside text, drafting structured text, and working through complex questions. Since its output modality is text, its described responses are textual; the listing does not identify audio generation or other output modalities. The context limit may help when a task requires retaining substantial input in one interaction, while the output limit allows for extended written results. The relevant task should fit the supported inputs and available tool configuration.
Key features
- Accepts text, images, and files; produces text
- Has a context window of 1,050,000 tokens
- Supports reasoning and tools
- Supports structured outputs and response_format
- Allows up to 128,000 output tokens
Typical uses
- Analyzing long documents
- Interpreting images with text prompts
- Working through complex questions
- Drafting structured text
- Tool-assisted workflows
GPT-6 Luna Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| 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 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-6-luna-pro: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 a task costs | Cost |
|---|---|
| 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 |
GPT-6 Luna Pro specifications
| Model id | openai/gpt-6-luna-pro |
|---|---|
| Version | gpt-6-luna-pro-20260922 |
| Context window | 1,050,000 tokensAbout 787,500 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 22 Sep 2026 |
| Input types | file, image, text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied 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 Pro yet.
Compare GPT-6 Luna Pro
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.