GPT-5.6 Luna
GPT-5.6 Luna 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: chat, classification and lightweight agentic workflows.
Price checked · source: OpenRouter
What GPT-5.6 Luna is
OpenAI GPT-5.6 Luna is a model in OpenAI’s GPT-5.6 series, described as suited to high-volume, latency-sensitive work. It accepts text, images, and files, and returns text. Its context window is 1,050,000 tokens, and its maximum output is 128,000 tokens. The stated context can accommodate lengthy input within the model’s limit, while the output limit allows it to return extended text. The catalog identifies chat, classification, and lightweight agentic workflows as intended task areas, without narrowing those uses to a particular industry or data type.
GPT-5.6 Luna supports reasoning, tool use, structured outputs, and response formats. These options make it applicable to interactive text exchanges, categorizing information, and workflows that use tools. Structured-output and response-format support can suit applications that need a defined response shape, while reasoning support is relevant to tasks involving considered text responses. Image and file inputs allow a request to include more than typed text, although the catalog does not specify particular image or file operations. The model produces text rather than image or other listed output modalities. Its combination of a long context, text output, and support for these interaction features fits tasks that process substantial context or run at high volume with latency sensitivity. The catalog does not provide more detailed modality, tool, or formatting specifications.
Key features
- Accepts text, image, and file inputs and produces text
- Has a context length of 1,050,000 tokens
- Supports a maximum output of 128,000 tokens
- Supports reasoning, tools, structured outputs, and response formats
Typical uses
- Chat
- Classification
- Lightweight agentic workflows
- Processing lengthy text and file inputs
GPT-5.6 Luna 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: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 specifications
| Model id | openai/gpt-5.6-luna |
|---|---|
| Version | gpt-5.6-luna-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 yet.
Compare GPT-5.6 Luna
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.