Positioning and capabilities
GPT-6.1 Terra is a fast, efficient model for visual reasoning, computer use and natural writing. It accepts text and image inputs and produces text outputs. It supports configurable reasoning effort, function calling, structured outputs and tools including web search, file search, code interpreter and computer use. Tool calling requires the Responses API. (openai.com)
Uses
OpenAI describes uses including matching product photos to catalog entries, interpreting technical drawings, interacting with application screens, drafting and revising text, and automating invoice processing and data entry. (openai.com)
Limits and availability
- Context window: 1,050,000 tokens; maximum output: 128,000 tokens.
- Knowledge cutoff: June 1, 2026.
- Audio and video inputs are not supported; fine-tuning is not supported.
- In ChatGPT, the model is available in Work and Codex, not Chat. UAE inference residency is not supported; this restriction concerns where inference runs, not the user's location. (developers.openai.com)
Release date
October 26, 2026, according to OpenAI's model release notes. (help.openai.com)
OpenAI API pricing
Prices below are in USD per 1 million text tokens, checked November 15, 2026. Standard rates for prompts of up to 272,000 input tokens are: input $1.00, cached input $0.05, and output $5.00. Cache writes cost $1.25 for 30-minute retention or $2.50 for 12-hour retention. (developers.openai.com)
For prompts exceeding 272,000 input tokens, the entire request is charged at twice the applicable input and cache rates and 1.5 times the applicable output rate. Batch and Flex rates are 50% below Standard; Fast mode rates are twice Standard. Regional processing adds 10% where available. Tool usage can incur separate charges, and API usage is billed separately from ChatGPT subscriptions. (developers.openai.com)