GPT-6.1 Terra

// Overview

GPT-6.1 Terra is the mid-sized model in OpenAI's GPT-6 family, released on October 26, 2026 as the successor to GPT-5.6 Terra. OpenAI's four tiers run, from cheapest to most capable, Luna, Terra, Sol and Astra. OpenAI's API documentation describes GPT-6.1 Terra as a fast, efficient model for detailed visual reasoning, precise computer use and natural writing: it reads what is on screen and acts across apps by clicking, typing and switching between them.

The model accepts text and image input and returns text, with a 1,050,000-token context window (922,000 input tokens and up to 128,000 output tokens) and a knowledge cutoff of June 1, 2026. It is served on the Chat Completions, Responses and Batch endpoints and supports streaming, structured outputs, function calling, file search, web search and prompt caching. On the Responses API it can use hosted tools including computer use, code interpreter, hosted shell, apply patch, skills, MCP and tool search. Reasoning effort can be set to none, low, medium (the default), high, xhigh or max.

The standard API price is $1.00 per 1M input tokens, $0.05 per 1M cached input tokens and $5.00 per 1M output tokens, half of GPT-6.1 Sol's input rate and less than half of GPT-5.6 Terra's $2.00 input and $12.00 output. Batch and Flex processing halve that again to $0.50 and $2.50. At launch it was available in the API as gpt-6.1-terra and to Plus, Pro, Enterprise and Edu users in ChatGPT Work and Codex. 9to5Mac reports that on OpenAI's internal set of error-inducing prompts its error rate at low reasoning effort fell from 53.6% for GPT-5.6 Terra to 16.7%, and to 4.3% at maximum effort.

// Pricing

Standard tier, short context. Batch and Flex are $0.50 input, $0.025 cached input and $2.50 output; Priority is $2.00, $0.10 and $10.00. GPT-5.6 Terra is $2.00 input and $12.00 output.

Pricing source ↗

// Strengths

• Computer use and visual reasoning across apps at $1.00 input and $5.00 output per 1M tokens
• Cached input at $0.05 per 1M tokens, with Batch and Flex rates at half the standard price
• 1.05M-token context window with up to 128K output tokens
• Hosted tools on the Responses API, including computer use, code interpreter, hosted shell, MCP and tool search
• Reasoning effort configurable from none through max

// Best for

• Reach for it for computer-use agents that operate browsers and desktop apps at high volume, where Sol or Astra pricing is hard to justify.
• Reach for it for screenshot and document understanding that needs visual reasoning over long inputs.
• Reach for it for everyday writing and communication tasks in ChatGPT Work.
• Reach for it for bulk agent workloads on the Batch or Flex tiers at $0.50 input and $2.50 output per 1M tokens.

// How to access

// GPT (Flagship / Thinking) — every version

The full lineage of the GPT (Flagship / Thinking) line, newest first. Every version has its own page — click any to compare specs, benchmarks and pricing.