GPT-5.6 Luna Pro
GPT-5.6 Luna Pro is a large language model made by OpenAI, added to the catalog on 9 Jul 2026. It has a context window of 1,050,000 tokens and costs $0.20 per 1M input tokens and $1.20 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: reviewing long documents, reasoning through complex tasks and working with image-and-text inputs.
Price checked ยท source: OpenRouter
What GPT-5.6 Luna Pro is
OpenAI GPT-5.6 Luna Pro is a text-generating model configured for reasoning-intensive work. It uses the same underlying model as GPT-5.6 Luna, served with reasoning mode set to pro; the provider describes this setting as intended to give higher-quality responses on complex tasks. Its outputs are text, while its inputs can include text, files, and images.
It has a context window of 1,050,000 tokens and can produce up to 128,000 tokens in an output. This large context can accommodate extensive source material in one interaction, including long documents or files, while leaving room for a detailed text response. Image input also makes it suitable for requests that combine visual material with written instructions, with text as the resulting output.
The model supports reasoning, tools, structured outputs, and response_format. These capabilities suit tasks that need problem solving, tool-assisted workflows, or responses shaped to a specified format. Its long context also fits work such as reviewing lengthy documents, synthesizing information across supplied materials, and drafting or revising text from detailed briefs. The model can take text, files, and images as source material, then return text responses, making it relevant when a task draws on more than one kind of input. Its listed generated modality is text.
Key features
- Accepts text, file, and image inputs; produces text.
- Has a context window of 1,050,000 tokens.
- Supports outputs up to 128,000 tokens.
- Supports reasoning and tool use.
- Supports structured outputs and response_format.
Typical uses
- Reviewing long documents
- Reasoning through complex tasks
- Working with image-and-text inputs
- Generating structured text outputs
- Tool-assisted workflows
GPT-5.6 Luna Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.20 | $0.10 |
| Output, per 1M tokens | $1.20 | $0.60 |
| Cached input read, per 1M tokens | $0.02 | $0.01 |
| Cache write, per 1M tokens | $0.25 | n/a |
| Web search, per search | $0.01 | $0.01 |
| Input above 272,000 prompt tokens, per 1M | $0.40 | $0.20 |
| Output above 272,000 prompt tokens, per 1M | $1.80 | $0.90 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-5.6-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 9 Jul 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0060 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0084 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.032 |
GPT-5.6 Luna Pro specifications
| Model id | openai/gpt-5.6-luna-pro |
|---|---|
| Version | gpt-5.6-luna-pro-20260709 |
| Context window | 1,050,000 tokensAbout 787,500 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | 2026-02-16 |
| Added to catalog | 9 Jul 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-5.6 Luna Pro yet.
Compare GPT-5.6 Luna Pro
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.