None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.
Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
😢 Every free AI generation costs us real GPU money. We pay out of pocket to keep this free for you.
💎 Upgrade to Pro and unlock:
- ✓HD Download
- ✓No Watermark
- ✓Unlimited Generations
GPT-6.1 Terra
GPT-6.1 Terra pairs sharp visual reasoning with precise computer use, faster video edits, and 50% lower API pricing than GPT-5.6 Terra.
All Tools
Discover our comprehensive AI-powered animation toolkit
Why Teams Pick GPT-6.1 Terra
A fast, efficient model that pairs detailed visual reasoning with precise computer operation, so video and desktop work finishes in fewer steps.
- Visual Reasoning and Computer UseGPT-6.1 Terra reads technical drawings and animation frames, then operates the apps needed to act on them.
- Half the API PriceStandard API pricing sits 50% below GPT-5.6 Terra and GPT-6.1 Sol, so invoice reading and data entry can run at scale.
- More Done per PlanIn ChatGPT work and Codex, the same allowance covers more tasks than GPT-5.6 Terra, and far more than GPT-6 Astra.
How to Work with GPT-6.1 Terra
Three steps take a rough brief all the way to a finished clip.
GPT-6.1 Terra Benchmarks
Computer use, visual reasoning, factual accuracy, and coding strength, measured across Agents' Last Exam, MMMU-Pro, OSWorld 2.1, and Terminal-Bench.
Agents' Last Exam
At medium reasoning, GPT-6.1 Terra scores 15 points above GPT-5.6 Terra on computer-use tasks at about a third of the cost.
MMMU-Pro
It outperforms GPT-5.6 Terra at every reasoning setting and nears GPT-6 Astra and GPT-6.1 Sol for far less.
OSWorld 2.1
At medium reasoning it already beats GPT-5.6 Terra's best score on multi-step desktop tasks such as building a 3D model from drawings.
Factual Accuracy
On error-prone prompts, mistakes fall from 53.6% to 16.7% at low reasoning and to 4.3% at maximum reasoning.
Terminal-Bench 4.0
At maximum reasoning it solves 50.3% of command-line tasks, more than double GPT-5.6 Terra's 21.5%.
Terminal-Bench-Science 0.1
It beats GPT-6.1 Sol at lower cost and lands within five points of Claude Opus 5.5 on code-driven science tasks.
GPT-6.1 Terra — FAQ
Common questions about pricing, availability, accuracy, and computer-use performance.
What is GPT-6.1 Terra?
GPT-6.1 Terra is a fast, efficient model built for detailed visual reasoning, precise computer operation, and clearer, more natural writing.
How much does the API cost?
Standard pricing is $1 per million input tokens, $0.05 per million cached input tokens, and $5 per million output tokens — about half of GPT-5.6 Terra and GPT-6.1 Sol.
Where can I use GPT-6.1 Terra?
Plus, Pro, Enterprise, and Edu plans include it in ChatGPT work and Codex; developers call gpt-6.1-terra through the OpenAI API.
How does it compare with GPT-5.6 Terra?
It gains 15 points on Agents' Last Exam at medium reasoning, cuts the API price by 50%, and finishes tasks over three times faster than GPT-6 Astra and GPT-6.1 Sol.
Does it make fewer factual errors?
Yes. On internal error-prone prompts the mistake rate drops from 53.6% to 16.7% at low reasoning, and to 4.3% at maximum reasoning.
How is it kept safe?
GPT-6.1 Terra meets the 'severe' cybersecurity threshold in the Preparedness Framework, keeps GPT-6 Astra's safeguards, and resists prompt injection.
Try GPT-6.1 Terra Today
Use GPT-6.1 Terra in ChatGPT work, Codex, or the API — $1 per million input tokens, $5 per million output tokens.