GPT-6.1 Terra matches GPT-6 Astra on agent tasks at one-tenth the price, and it's in ChatGPT now
OpenAI released GPT-6.1 Terra, a fast mid-tier model built for computer use: it reads what's on screen, clicks and types across apps, and writes more naturally than GPT-5.6 Terra. On Agents' Last Exam, OpenAI's test of agents doing real office software work, OpenAI says Terra performs on par with GPT-6 Astra at one-tenth Astra's price per token and finishes tasks over three times faster than both Astra and GPT-6.1 Sol. Standard API prices are 50% lower than GPT-5.6 Terra: $1 per million input tokens and $5 per million output tokens.
Why it matters
Agents that fill in forms, read invoices or click through apps all day get expensive fast. A model that does this work at near-flagship quality for a fraction of the cost makes high-volume automation realistic, and your ChatGPT or Codex allowance covers more tasks.
Who it's for
ChatGPT Plus, Pro, Enterprise and Edu users, Codex users, and developers running computer-use or high-volume agent jobs on the API.
How to try it
- In ChatGPT Work or Codex, open the model picker and choose GPT-6.1 Terra once it reaches your account.
- Give it a screen-based chore, like copying details from a PDF invoice into a spreadsheet, and check the first few results by hand.
- Developers: switch the model name to gpt-6.1-terra and compare cost per task against your current model before moving everything over.
Plan & availability: Rolling out from October 26, 2026 to Plus, Pro, Enterprise and Edu users in ChatGPT Work and Codex. In the API it's gpt-6.1-terra at $1 input / $5 output per million tokens (cached input $0.05; Batch and Flex 50% off). OpenAI still recommends GPT-6.1 Sol or GPT-6 Astra for deep research and the hardest coding.
Source: @OpenAI on openai.com ↗
Written by AgentStackList from the original post. Checked Oct 27, 2026. Features, plans and availability can change, so confirm on the source before you rely on it.
gpt-6-1-terracomputer-useopenai-apicodex
More ChatGPT tricks
- OpenAI Private Intelligence: zero data retention, private inference and approval rules for business agents · Oct 30
- An OpenAI model slipped onto the live internet during training. Monitors caught it in 15 minutes · Oct 29
- OpenAI backed down: the Pro 200 cut is cancelled and Pro 100 and 500 get double the Codex usage · Oct 29
- OpenAI rewrote ChatGPT's rulebook around 5 values and stopped calling it "the assistant" · Oct 29
Agent Stack Weekly · free
Get the week's best AI tricks
Limit and pricing changes, new MCP servers, and setup fixes for Claude Code, Codex, Cursor, Copilot and Antigravity.
No spam. Unsubscribe anytime. Read past issues