Developed by Open AI, GPT-6.1 Terra Pro is a chat model engineered for complex reasoning tasks. It utilizes a pro mode that allocates more reasoning tokens per request to improve answer quality.
The model supports diverse modalities including text and images. It is built to handle large amounts of information through its extensive context window and file input capabilities.
The model utilizes a dedicated mode that spends more reasoning tokens to provide higher-quality answers.
Users can provide text, images, and files as inputs for the model to process.
The model supports a context window of 1.05M tokens for handling extensive information.
Features include parallel tool calls, structured output, and streaming capabilities.
Analyzing complex documents and files.
Interpreting and reasoning about image content.
Generating structured outputs for technical tasks.
Processing long-form content with large context requirements.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-6.1-terra-pro", "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-pro", "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-pro","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: $2.116 / 1M input tokens, $0.1058 / 1M cached input tokens and $10.58 / 1M output tokens. Cache writes cost $2.645 / 1M tokens. Reasoning tokens are billed as output. Prompts above 272,000 tokens are billed at $4.232 input and $15.87 output per 1M tokens.
Analyzing complex documents and files.
Interpreting and reasoning about image content.
Generating structured outputs for technical tasks.
Processing long-form content with large context requirements.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-6.1 Terra Pro This page | Complex reasoning tasks requiring high-quality output. | |||
| Complex coding and agentic work | ||||
| Everyday coding and agents | ||||
| Everyday coding + agents | ||||
| Agentic coding & long-horizon work |
GPT-6.1 Terra Pro costs $2.116 / 1M tokens for input and $10.58 / 1M tokens for output on AI/ML API. Cached input is billed at $0.1058 / 1M tokens.
The model supports image and text inputs and produces text outputs.
Pro mode spends far more reasoning tokens per request to achieve higher-quality answers.
Yes, the model supports file input as part of its capabilities.
The model supports a maximum output of 128,000 tokens.