OpenAI GPT-5.6 Luna targets cost-sensitive, high-volume workloads — the cheapest and fastest tier of the GPT-5.6 family, while keeping the same 1,050,000-token context window and 128,000-token max output. Supports text and image input, web search, and reasoning effort / summary display options. Ideal for chatbots, classification, routing, batch summarization, and other tight-loop tools where per-call cost matters most; upgrade to Terra or Sol when a task needs more capability. If you need to search the web for information, please turn on the "Web Search" switch. Prompt example 1: Label each review as positive, negative or neutral: works great; shipping was slow; it's okay; nice packaging; broke after two days. Prompt example 2: Summarize in one sentence: System maintenance is scheduled this Saturday from 8 a.m. to noon, and the member area will be unavailable during that time. Prompt example 3: Convert these dates to YYYY-MM-DD format: March 5, 2026; 2026/7/10; Dec 1st 2026. Prompt example 4: Fix the spelling mistakes and output only the corrected sentence: The resturant's servise was excellent, and we will definately come back. Prompt example 5: You are an online bookstore's support agent. Answer in two sentences: How soon do orders ship? Can I pick up at a convenience store? Prompt example 6: Turn these article titles into lowercase, hyphenated URL slugs: Autumn camping gear picks; Pour-over coffee for beginners; Ten home storage tips. Prompt example 7: Find the duplicate names in this club member list and count the actual number of people: Amy Lin, David Chen, Kevin Wu, Amy Lin, Grace Chang, David Chen. Prompt example 8: (Upload a product photo, jpg) Write alt text of up to 20 words for this image, for web accessibility. Prompt example 9: Scale this recipe from four servings to two: 400 g flour, 4 eggs, 300 ml milk, 60 g sugar. Prompt example 10: Convert 10 a.m. on November 3, Taipei time, into local time in Tokyo, London and New York, shown in a table. Maximum context window (input and output combined): about 1,050,000 tokens. Maximum total input per request (including history): 922,000 tokens. Maximum output per reply: about 128,000 tokens (model reasoning, if any, counts toward this limit). Maximum total upload size per request: 512MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: gif, jpeg, jpg, png, webp. Maximum number of images: 1500. Maximum size per image: 50MB. Maximum total image size per message: 384MB (text and history share the same request size limit; uploads close to the limit may still be rejected). Image dimensions: 200 to 8,000 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Text/Image Pricing: Low Fast Mode: uses 2x credits Continuous conversation: Supported AI can make mistakes. Please verify important information.