GPT 5.6 Luna
GPT 5.6 Luna is a text and image-input model from OpenAI with a 1,050,000-token context window.
OpenAILarge-context text and vision generation from OpenAI
GPT 5.6 Luna is a large language model developed by OpenAI, released in July 2026. It accepts both text and image inputs and generates text outputs, with a context window of 1,050,000 tokens and a maximum response size of 128,000 tokens. The model exposes a configurable reasoning effort setting, allowing users to adjust how much computation the model applies to a given request.
GPT 5.6 Luna is suited for tasks that require processing large volumes of text in a single pass, such as analyzing lengthy documents, codebases, or multi-turn conversations with extensive history. Its image input support makes it applicable to workflows that combine visual and textual information. The adjustable reasoning effort input gives developers a degree of control over the trade-off between response depth and latency.
What GPT 5.6 Luna supports
Large Context Window
Processes up to 1,050,000 tokens in a single request, enabling analysis of long documents, large codebases, or extended conversation histories without truncation.
Image Input
Accepts image inputs alongside text, supporting workflows that require understanding or describing visual content within a prompt.
Configurable Reasoning Effort
Exposes a reasoning effort selector that lets users tune how much computation the model applies, offering control over the depth-versus-latency trade-off.
Long-Form Text Generation
Generates responses of up to 128,000 tokens, making it suitable for producing detailed reports, long-form drafts, or extensive code outputs in a single call.
Ready to build with GPT 5.6 Luna?
Get Started FreeCommon questions about GPT 5.6 Luna
What is the context window size for GPT 5.6 Luna?
GPT 5.6 Luna has a context window of 1,050,000 tokens, meaning it can process up to that many tokens of combined input and conversation history in a single request.
What is the maximum response length?
The model supports a maximum response size of 128,000 tokens per output.
Does GPT 5.6 Luna support image inputs?
Yes. The model accepts image inputs in addition to text, allowing prompts that include visual content.
What does the Reasoning Effort setting do?
Reasoning Effort is a configurable input that adjusts how much computation the model applies when generating a response. Lower effort may reduce latency, while higher effort may improve response depth.
When was GPT 5.6 Luna released and who publishes it?
GPT 5.6 Luna was released in July 2026 and is published by OpenAI.
Parameters & options
Explore similar models
OpenAIGPT 5.6 Terra
GPT 5.6 Terra is a text generation model from OpenAI with a 1,050,000-token context window and image input support.
OpenAIGPT 5.6 Sol
GPT 5.6 Sol is a text generation model from OpenAI with a 1,050,000-token context window and image input support.
OpenAIGPT-5.5
GPT-5.5 is a multimodal text generation model from OpenAI with a 1,000,000-token context window and adjustable reasoning effort.
DeepSeekDeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a text generation model from DeepSeek with a 1,048,576-token context window and configurable reasoning effort.
GoogleGemini 3.7 Flash
Gemini 3.7 Flash is a text generation model from Google with a 1,048,576-token context window and configurable thinking levels.
NvidiaNemotron 3.5 Lightning
Nemotron 3.5 Lightning is a text generation model from Nvidia designed for fast reasoning with a 262,144 token context window.
OpenAIo1
o1 is a text generation model from OpenAI that uses internal chain-of-thought reasoning before producing responses.
Start building with GPT 5.6 Luna
No API keys required. Create AI-powered workflows with GPT 5.6 Luna in minutes — free.