GPT-6.1 Terra

GPT-6.1 Terra is OpenAI’s October 26, 2026 text-output model for visual reasoning, computer use and writing. API access and eligible ChatGPT Work/Codex plans have separate limits.

GPT-6.1 Terra explainer
Access, fit and evaluation limits.
GPT-6.1 Sol
Separate model and pricing.
AI Model API
Provider contracts and request boundaries.

Platform: OpenAI

Language ModelCoding AssistantVisionAgent Workflows

OpenAI API; eligible Work/Codex plans, separate allowances.

$1/M input, $0.05 cached input, $5 output; cache writes $1.25/30m or $2.50/12h; >272K input doubles input/cache and 1.5x output for full request.

Scoped Terms

🚀Function Overview

GPT-6.1 Terra accepts text and images with 1.05M context and 128K output; standard API rates are $1 input, $0.05 cached input and $5 output per million tokens.

Key Features

1,050,000 context tokens; 128,000 maximum output; knowledge cutoff June 1, 2026.
Text and image input, text output; no native audio or video input/output.
reasoning.effort: none, low, medium (default), high, xhigh, max.
Tool calling requires Responses API; a Chat Completions request does not inherit Responses tools.
Standard cache writes: $1.25/M for 30 minutes; $2.50/M for 12 hours.
Above 272K input tokens, full-request input/cache rates double and output rates increase 1.5×.
Fast 2× Standard; Batch/Flex separate half-price modes; regional processing adds 10% where available.
Work/Codex rollout, workspace eligibility and UAE inference residency restriction are separate from direct API access.

Use Cases

•Visual analysis and supervised computer workflows.
•Document drafting and revision.

⚙️Input Parameters

model

string

Use gpt-6.1-terra.

input

object

Text or documented image content for Responses API.

reasoning.effort

string

none, low, medium (default), high, xhigh or max.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "gpt-6.1-terra",
  "input": "Read the supplied document, identify the stated constraints, and draft a short source-linked summary.",
  "reasoning": {
    "effort": "medium"
  }
}

Output Results

Illustrative request or command only. GetLLMs has not executed this example or verified model output.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: OpenAI API; eligible Work/Codex plans, separate allowances.
Commercial Use: Hosted service use follows the selected provider terms. This record does not establish a downloadable-weight license.
Pricing: $1/M input, $0.05 cached input, $5 output; cache writes $1.25/30m or $2.50/12h; >272K input doubles input/cache and 1.5x output for full request.
Platform: OpenAI