An OpenAI model for visual reasoning, precise application workflows, clear writing, and focused code changes.
Use openai/gpt-6.1-terra through the sjolt LLM API.
openai/gpt-6.1-terraToken rates
openai/gpt-6.1-terraSimilar Models
An Anthropic model for careful coding, long-document analysis, and visual understanding with optional adaptive thinking.
An Anthropic model for coding, long-context knowledge work, and visual understanding with adaptive thinking.
An Anthropic model for responsive coding, long-document analysis, and text-and-image understanding with adaptive thinking.
Model overview
Compare images, understand application screens, and turn source material into clear writing. The artwork illustrates these workflows; it is not image output from GPT-6.1 Terra.
Provide a screenshot, the relevant code, and the intended behavior. Ask for a scoped change, explain the visual evidence, and verify the result against your requirements.
Bring up to 1,050,000 context tokens to compare source documents and draft or revise text. Specify the audience, tone, and structure, and keep conclusions grounded in the supplied material.
Include product photos, technical drawings, or application screenshots with a concrete comparison task. Ask for observable differences and a precise next step. Use Responses when connecting your own application tools.
Model characteristics
Visual reasoning, application tool workflows, scoped code changes, and natural writing.
Up to 1,050,000 context tokens.
The model supports up to 128,000 output tokens, including reasoning.
Select none, low, medium, high, xhigh, max; medium is the default. Choose none to disable reasoning.
FAQ
Use it to compare product images, interpret diagrams, work with application screenshots, revise text, and make focused code changes. State the task, constraints, and expected response structure.
Yes. Attach images in the Playground or send native image blocks through Chat Completions or Responses. Responses are text; native image fields are forwarded for upstream validation.
Select none, low, medium, high, xhigh, max. Choose none to disable reasoning, with medium as the Playground default.
The model supports 1,050,000 context tokens and up to 128,000 output tokens. Input and generated reasoning share the available context with the final answer.
Use model openai/gpt-6.1-terra through OpenAI-compatible Chat Completions or Responses. Use Responses for application tool workflows. Both protocols accept streaming and non-streaming requests.
Include previous response items in the next input. Preserve reasoning.encrypted_content unchanged with the conversation and application tool results.