Developed by OpenAI, GPT-6.1 Terra is a chat model optimized for efficiency and versatility. It excels at processing both text and images to support a wide range of analytical and creative tasks.
The model features a large context window and advanced capabilities like parallel tool calls and vision. It is designed to integrate seamlessly into workflows requiring structured data and reasoning.
The model processes image inputs to perform complex visual analysis and reasoning tasks.
Supports parallel tool calls and structured output through the Responses API for enhanced integration.
Features a 1.05M-token context window to handle extensive information and long-form content.
Accepts both text and image inputs to provide comprehensive responses across different modalities.
Analyze complex images to extract insights and perform visual reasoning.
Automate computer use tasks by leveraging parallel tool calling.
Generate natural writing based on large documents or image data.
Produce structured output for data processing and integration workflows.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-6.1-terra", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "openai/gpt-6.1-terra", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-6.1-terra","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Billed per token: $1 / 1M input tokens, $0.05 / 1M cached input tokens and $5 / 1M output tokens. Cache writes cost $1.25 / 1M tokens. Reasoning tokens are billed as output. Prompts above 272,000 tokens are billed at $2 input and $7.5 output per 1M tokens.
Analyze complex images to extract insights and perform visual reasoning.
Automate computer use tasks by leveraging parallel tool calling.
Generate natural writing based on large documents or image data.
Produce structured output for data processing and integration workflows.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-6.1 Terra This page | Visual reasoning and complex tool-based workflows. | |||
| Complex coding and agentic work | ||||
| Everyday coding and agents | ||||
| Cost-sensitive workloads on auto-update | ||||
| Agentic coding and codebase tasks |
GPT-6.1 Terra costs $1 / 1M tokens for input and $5 / 1M tokens for output on AI/ML API. Cached input is billed at $0.05 / 1M tokens.
The model supports both text and image inputs.
The model features a 1.05M-token context window.
Yes, it supports parallel tool calls using the Responses API.
The model supports a maximum output of 128,000 tokens.
