OpenAI's GPT-6.1 Terra: Half the Price, Built to Actually Use Your Computer

OpenAI released GPT-6.1 Terra on October 26, 2026, and the headline is refreshingly boring in the best way: it is cheaper, faster, and built for the unglamorous work that actually fills a developer's day. Not a flagship flex. A workhorse price cut for the model that clicks buttons, reads forms, and turns drawings into documents.

If you run agents that touch real screens and real documents at volume, this is the model change that moves your bill. Here is what it is, what it costs, and where it does not belong.

Disclosure: no affiliate links in this article. All benchmark figures below are OpenAI's own measurements from its launch announcement — they have not been independently verified yet, and I say so wherever they appear. I have not run the model hands-on; this is researched analysis, not a benchmark I performed.

Terra replaces GPT-5.6 Terra in OpenAI's lineup. It sits in the middle: above GPT-6 Luna, the cheapest model, and below GPT-6.1 Sol and the flagship GPT-6 Astra.

It is a reasoning model built for high-volume visual and computer-use work. It takes text and image input, has a 1.05-million-token context window with up to 128,000 output tokens, and — this is the point — it can operate a computer: look at a screen, click, type, and move between applications the way a person would.

It is available to Plus, Pro, Enterprise and Edu users in ChatGPT Work and Codex, and to developers through the API as gpt-6.1-terra. Amazon Web Services made it available on Bedrock the same day. It is not in regular Chat, and no free tier is listed — this is a paid-plans-and-API model.

Through the Responses API it supports tools including computer use, web search, file search, code interpreter, hosted shell and MCP. OpenAI's own example workloads tell you exactly who it is for: drafting proposals, interpreting technical drawings, filling out forms, entering invoices into accounting software, matching product photos to catalogue entries, and editing video by scene.

Standard API pricing per million tokens:

So Terra is half the price of both its predecessor and Sol, and roughly one-tenth the token price of Astra. Independent developer write-ups put it the same way: almost half the price of GPT-5.6 Terra and GPT-6.1 Sol, and around 10x the price of GPT-6 Luna.

Two pricing details matter if you run long or batched workloads:

Again: these are OpenAI's claims, not independent results. But the direction is consistent, and it is the reason this launch matters.

On Agents' Last Exam — a set of professional tasks like turning architectural drawings into a 3D model — OpenAI says Terra at medium reasoning effort scores 15 percentage points higher than GPT-5.6 Terra at about one-third the cost, and performs on par with GPT-6 Astra at only one-tenth its price per token. It also says Terra finishes tasks more than three times faster than Astra or Sol.

At maximum effort, OpenAI says Terra is over three times as token-efficient as Anthropic's Claude Opus 5.5 at a quarter of its price per token — working out to roughly a 9x lower cost per task.

On Terminal-Bench 4.0, a coding test, Terra solved 50.3% of tasks at maximum effort, up from 21.5% for its predecessor. On an internal set of prompts designed to trigger errors, the error rate at low reasoning effort fell from 53.6% to 16.7%. On OSWorld 2.1, which tests desktop-application use, Terra beat its predecessor's best score at medium reasoning effort while costing less per task.

The honest read: cheaper and more capable at once, on the vendor's own tests. Independent testing will tell us how much of that survives contact with real, messy desktops. Treat every number above as a claim to verify, not a fact to budget on blindly.

Use Terra for: high-volume computer work. Invoice entry, form filling, document processing, proposal drafting, reading technical drawings, matching photos to catalogue entries, time-coded video logs. Anywhere the work is repetitive, screen-bound, and billed by the token, Terra's price-to-capability ratio is now the best in OpenAI's lineup for that job.

Keep Sol or Astra for: the hardest coding and research. OpenAI itself still points complex coding to Sol or Astra, and independent summaries agree: on Terminal-Bench, Terra's 50.3% trails Sol's 55.9% and Claude Sonnet 5.5's 70.6%. Terra is not the leaderboard model. It is the model that handles most of the volume in a real system.

Keep Luna for: the simplest, cheapest tasks. At $0.10 input and $0.50 output, Luna is still roughly a tenth of Terra's price. If the task does not need visual reasoning or computer use, Luna remains the cheapest way to do it.

Terra is not exciting in the way a flagship launch is exciting, and that is exactly why it matters. The agent era does not live or die on the smartest model in the lineup. It lives on the cost per task of the model that does the routine work, thousands of times a day, without a human watching every step.

OpenAI just halved that cost for computer-use work while claiming it got better at it. If independent testing backs even half of that up, Terra becomes the default model for a huge class of agent workloads — not because it is the best model OpenAI makes, but because it is the cheapest one good enough for the job. And in production, "good enough, at half the price" wins far more often than "best, at ten times the price."

What is GPT-6.1 Terra? OpenAI's mid-tier model released October 26, 2026, built for visual reasoning and computer use — reading screens, filling forms, and automating everyday office tasks at a lower price than larger models.

How much does GPT-6.1 Terra cost? $1 per million input tokens, $0.05 per million cached input tokens, and $5 per million output tokens at standard rates — about half the price of GPT-6.1 Sol and its predecessor GPT-5.6 Terra.

How do I access GPT-6.1 Terra? In ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users, and through the API as gpt-6.1-terra. It is not in regular Chat, and no free tier is listed.

Is GPT-6.1 Terra better than GPT-6.1 Sol? For computer-use work, OpenAI's benchmarks say yes at every effort level, at far lower cost per task. For the most complex coding, Sol remains better — the best choice depends on your workload.

Is GPT-6.1 Terra free? No. OpenAI's announcement names paid plans only, and API use is billed per token.

Sources: OpenAI's GPT-6.1 Terra launch announcement and developer documentation, as reported by BusinessToday, Analytics India Magazine, MarkTechPost, ModelDex and developer Simon Willison's write-up. Benchmark figures are OpenAI's own and have not been independently verified.