GPT-6.1 Terra is out: what changed, and what it costs you

OpenAI calls Terra a significant step up from its previous Terra model, for the communication and computer-based work that fills a workday, from drafting proposals and interpreting technical drawings to filling out forms and editing videos.^[3]

Its standard API prices are $1 per million input tokens, $0.05 per million cached input tokens and $5 per million output tokens, 50% lower than GPT-6.1 Sol's and the previous Terra's.^[3][2]

Cached input costs 5% of the input price; cache writes cost $1.25 per million tokens for 30-minute retention and $2.50 for 12-hour retention.^[2]

A prompt of more than 272K input tokens is billed at twice the input and cache rates and 1.5 times the output rate for the whole request. Batch and Flex prices are 50% lower than Standard, and Fast mode costs twice as much.^[2]

Its context window is 1,050,000 tokens, a reply can run to 128,000 tokens, and its knowledge cutoff is June 1, 2026. It reads text and images and writes text; audio and video aren't supported.^[2]

Its reasoning effort runs from none through low, medium (the default), high and xhigh to max; OpenAI suggests starting at medium and raising it when the better answers are worth the time and tokens. GPT-6 Astra and GPT-6.1 Sol don't support none.^[2][1]

In OpenAI's API, tool calling needs the Responses API, where it supports web search, file search, code interpreter, computer use and MCP, beside function calling, structured outputs and streaming.^[2]

OpenAI reports that on Agents' Last Exam, a benchmark of professional computer-use tasks, Terra at medium reasoning effort scores 15 percentage points higher than the previous Terra at about one-third of the cost, and performs on par with GPT-6 Astra at one-tenth of its price per token.^[3]

On Terminal-Bench 4.0, a test of coding agents at the command line, OpenAI reports 50.3% for Terra at maximum reasoning effort, more than double the previous Terra's published 21.5%, and says GPT-6.1 Sol and GPT-6 Astra remain the better choice for the most complex coding.^[3]

In ChatGPT it's available from October 26 to Plus, Pro, Enterprise and Edu users in ChatGPT Work and Codex, where OpenAI says the same usage allowance covers substantially more tasks than with GPT-6.1 Sol or GPT-6 Astra.^[3]

OpenAI's GPT-6 guide places it between GPT-6.1 Sol, for balanced speed, cost and intelligence, and GPT-6 Luna, the fastest and most cost-effective, as its fast and efficient model. In the API it's gpt-6.1-terra.^[1]