GPT-6.1 Terra
GPT-6.1 Terra is an OpenAI model for everyday agentic, coding, and writing work. It accepts text, images, and files, supports reasoning and tool calling, and has a 1.05 million-token context window.
GPT-6.1 Terra specs and pricing
- Provider: OpenAI
- Released: October 26, 2026
- Context window: 1.1M tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: text
- Price: $1.00 input / $5.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-6.1 Terra is good at
- Understanding screenshots
- Everyday coding tasks
- Writing and editing
To-dos to try with GPT-6.1 Terra
- Describe the interface shown in this screenshot.
- Review this code and suggest changes to make it easier to read.
- Read this file and draft a concise summary.
FAQ
- Can GPT-6.1 Terra understand screenshots? Yes. It accepts image input, and OpenAI describes it as particularly strong at understanding screenshots.
- Can GPT-6.1 Terra use tools? Yes. It supports tool calling.
- How much does GPT-6.1 Terra cost? GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.5 credits ($1 = 100 credits).
- What is the context window of GPT-6.1 Terra? GPT-6.1 Terra can read up to 1.1M tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-6.1 Terra without coding? Yes. In todo.is you pick GPT-6.1 Terra as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.