OpenAI GPT-5.6 Terra balances intelligence and cost for general-purpose tasks — close to Sol in capability at a lower cost. Same 1,050,000-token context window and 128,000-token max output, with text and image input, web search, and reasoning effort / summary display options. A great default for drafting, translation, summarization, coding Q&A, and data wrangling; step up to Sol for the hardest problems, or down to Luna for high-volume low-stakes calls. If you need to search the web for information, please turn on the "Web Search" switch. Prompt example 1: Write an apology email to a client about a delivery delayed by a material shortage, giving November 15 as the new date, in a sincere, professional tone. Prompt example 2: Summarize in three key takeaways and translate into Traditional Chinese: New product sales grew steadily this quarter, but returns were high due to unclear sizing. Prompt example 3: Explain the difference between INNER JOIN and LEFT JOIN in SQL, with an example of each using a students table and a course enrollment table. Prompt example 4: Turn this event plan into text for a one-page slide: a family market in Taichung on November 8, about 30 booths and 2,000 visitors, with 10 volunteers needed. Prompt example 5: (Upload an employee attendance log, xlsx) Count each person's late arrivals and overtime hours in October, and list everyone late more than three times. Prompt example 6: How do I use a formula in Excel to find repeated customer names in column A and highlight them? Please explain step by step. Prompt example 7: Write a job posting for an administrative assistant at Northwind Ltd., covering duties, requirements and benefits, in about 200 words. Prompt example 8: Reading a 2 GB CSV file with pandas in Python runs out of memory. What are the ways to fix it? Give a short example for each. Prompt example 9: (Upload a photo of a whiteboard, jpg) Turn the whiteboard notes into meeting minutes listing decisions, action items and owners. Prompt example 10: Rewrite these video call steps so an older person can follow them, one short sentence per step: open the messaging app, tap the contact, tap the camera icon at the top right, wait for an answer. 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: Medium-high Fast Mode: uses 2x credits Continuous conversation: Supported AI can make mistakes. Please verify important information.