Skip to main content

openai/gpt-6.1-terra/chat

GPT 6.1 Terra reads screenshots and documents, then turns the supplied evidence into concise drafts or extracted fields. Terra defaults to a 4,096-token reply cap and permits 128,000; reserve part of that allowance for reasoning whenever effort is above none.

Input $1Output $5per 1 million tokensCached input $0.05Cache write $1.25Prompts over 272K tokensInput $2Cached input $0.10Cache write $2.50Output $7.50
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Input types
    Text
    Output types
    Text
    Input
    $1 / 1 million tokens
    Cached input
    $0.05 / 1 million tokens
    Output
    $5 / 1 million tokens
    Context
    1050K
    Max output
    128K

    $1/5per 1 million tokens · input / output

    basic

    For Terra, name the screenshot region and the fields you want extracted; keep unreadable values explicitly unknown rather than requesting a guess.

    • 1024
  • Input types
    Text
    Output types
    Text
    Input
    $1 / 1 million tokens
    Cached input
    $0.05 / 1 million tokens
    Output
    $5 / 1 million tokens
    Context
    1050K
    Max output
    128K

    $1/5per 1 million tokens · input / output

    tool-step

    For a Terra extraction workflow, define the functions your application can run and return their results under the original tool_call_id; this compatibility endpoint allows up to 128 definitions. Native OpenAI tool calls require Responses.

    • 1024
    • auto

This example starts at Input $1 / Output $5 per 1 million tokens. The Playground updates the estimate when you change the settings.