GPT-6.1 Terra

GPT-6.1 Terra is OpenAI's middle tier GPT-6 model, sitting between GPT-6.1 Sol and GPT-6 Luna on price. OpenAI describes it as "a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing," and suggests uses such as matching product photos to catalog entries, comparing technical drawings, acting on application screens, and drafting and revising text. OpenAI released it in the API on October 26, 2026.

Key facts

Sources: OpenAI's GPT-6.1 Terra model page, the API changelog and the GPT-6 guide, checked October 28, 2026.

Pricing details

Terra costs $1 per million input tokens and $5 per million output tokens, half of GPT-6.1 Sol's rate and ten times GPT-6 Luna's. Cached input costs $0.05, and cache writes cost $1.25 per million tokens for 30 minute retention or $2.50 for 12 hour retention. Prompts over 272,000 input tokens cost twice the input and cache rates and 1.5 times the output rate. Batch and Flex cost half, Fast mode costs double, and regional processing adds 10 percent where available.

Where to use GPT-6.1 Terra

• API: on the OpenAI API through the Responses API, Chat Completions and Batch. Tool calling, including computer use, needs the Responses API. Reasoning effort runs from none to max, with medium as the default.
• Not supported: audio and video input, fine tuning, and the Realtime API.

OpenAI's GPT-6 guide suggests that teams moving from GPT-5.6 Terra test both models on the same images and workflows at the same reasoning effort before switching.

How it compares

Terra fills the gap between GPT-6.1 Sol at $2 and $10 and GPT-6 Luna at $0.10 and $0.50. Our GPT-6 Sol vs Astra vs Luna guide explains where each model fits.

Who should use it

Try Terra when Luna is too weak for image heavy or screen based work but Sol costs more than the task is worth. For the hardest agentic and scientific work, step up to Sol or GPT-6 Astra. See the release timeline for every GPT-6 launch.