OpenAI
Operational· checked every few minutes

GPT-6.1 Terra API

GPT-6.1 Terra API: OpenAI's fast mid-tier model for agents, vision and everyday work.

Price per 1M tokens75%off
Input
$0.25$1.00
Output
$1.25$5.00
Input, long prompts
$0.50$2.00
Output, long prompts
$1.875$7.50
Cached input
$0.0125
Get your API keyTry it in the playground
Model IDgpt-6.1-terra
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="gpt-6.1-terra",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs

Context window
1.05M tokens
Max output
128K tokens
Reasoning
none to max
Input
Text, Image
Released
Oct 26, 2026
Status
Operational

Pricing

GPT-6.1 Terra API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayOpenAI list
Input
per 1M tokens
$0.25$1.00
Output
per 1M tokens
$1.25$5.00
Input, long prompts
per 1M tokens
$0.50$2.00
Output, long prompts
per 1M tokens
$1.875$7.50
Cached input
per 1M tokens
$0.0125—

Prompts over 272K tokens cost 2 times the input rates, cached input included, and 1.5 times the output rate, the way OpenAI bills them. Streaming, tool calls and structured outputs cost nothing extra.

Every GPT model and price
Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$25.00
OpenAI list price
$100.00
You save every month$75.00

$900.00 a year

Overview

What is GPT-6.1 Terra?

GPT-6.1 Terra is OpenAI's mid-tier GPT-6.1 model, released on October 26, 2026, for computer use, visual reasoning, coding and everyday work. OpenAI says it performs on par with GPT-6 Astra at one-tenth of Astra's list price per token. The GPT-6.1 Terra API on Zurelay serves it through one OpenAI-compatible endpoint, below OpenAI's list price.

GPT-6.1 Terra is the successor to GPT-5.6 Terra, released by OpenAI on October 26, 2026, four weeks after GPT-6.1 Sol. OpenAI describes it as a fast, efficient model that understands what is on screen, takes action across apps and writes naturally, and calls it a significant step up from GPT-5.6 Terra. The GPT-6.1 Terra API on Zurelay uses the model ID gpt-6.1-terra on an OpenAI-compatible Chat Completions endpoint.

The limits match the rest of the family: text and image input, text output, a 1,050,000-token context window, up to 922,000 input tokens and up to 128,000 output tokens. The knowledge cutoff is June 1, 2026, the latest of any GPT-6 model. Reasoning effort accepts none, low, medium (the default), high, xhigh and max. Unlike GPT-6.1 Sol, it takes none, for the fastest answers when a task needs no thinking.

OpenAI reports large gains over GPT-5.6 Terra. On Terminal-Bench 4.0 at maximum reasoning effort it solved 50.3% of tasks, against 21.5% for GPT-5.6 Terra. On OpenAI's factuality test at low reasoning effort, its error rate fell from 53.6% to 16.7%, and at maximum effort to 4.3%, close to GPT-6 Astra and GPT-6.1 Sol. OpenAI also says it finishes agent tasks over three times faster than GPT-6 Astra and GPT-6.1 Sol. These are OpenAI's own evaluations.

OpenAI lists it at half of GPT-6.1 Sol's and GPT-5.6 Terra's price per token, with cached input at 5% of the input rate. For the most complex coding work, OpenAI still recommends GPT-6.1 Sol or GPT-6 Astra. OpenAI's computer-use tool works only through its Responses API, which Zurelay doesn't offer yet. On Zurelay, Terra drives your own tools through function calling and reads screenshots you send as images.

Strengths

Where GPT-6.1 Terra shines. And what teams build with it.

01

Astra-level results on many tasks

OpenAI says GPT-6.1 Terra performs on par with GPT-6 Astra at one-tenth of Astra's list price per token.

02

Built for speed

OpenAI reports that it completes agent tasks over three times faster than GPT-6 Astra and GPT-6.1 Sol.

03

Far more factual than GPT-5.6 Terra

On OpenAI's factuality test at low reasoning effort, its error rate fell from 53.6% to 16.7%.

04

Half of GPT-6.1 Sol's list price

OpenAI lists it at half of GPT-6.1 Sol's price per token, and Zurelay charges less than that list rate.

Use cases

  • Screen and document understanding

    Read screenshots, invoices, forms and technical drawings, and turn what is on them into structured data.

  • Everyday agents

    Multi-step tool-calling workflows where speed and price per task matter more than the last bit of quality.

  • Writing and support

    Clear, natural drafts, replies and summaries at a price that suits high volume.

  • Fast answers with reasoning off

    Set reasoning_effort to none for classification, extraction and chat where the answer needs no thinking.

Get started

Call GPT-6.1 Terra in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use gpt-6.1-terra

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    gpt-6.1-terra

Works with the tools you already use

Compare

Similar models. All on the same key.

75%off

GPT-6.1 Sol

$0.50 / $2.50 per 1M tokens

Pick it for the most complex coding and agent work, where OpenAI recommends Sol over Terra.

GPT-6.1 Sol API
75%off

GPT-6 Astra

$2.50 / $12.50 per 1M tokens

Pick it when your tests show Astra's extra quality is worth ten times Terra's list price per token.

GPT-6 Astra API
73%off

GPT-5.6 Terra

$0.54 / $3.26 per 1M tokens

Pick it only to keep behavior you have already tested: 6.1 Terra costs less and scores higher.

GPT-5.6 Terra API

FAQ

GPT-6.1 Terra API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the GPT-6.1 Terra API cost?

On Zurelay, GPT-6.1 Terra costs $0.25 per 1M input tokens and $1.25 per 1M output tokens. OpenAI's list price is $1.00 input and $5.00 output, so you save 75%. Cached input tokens bill at $0.0125 per 1M, and reasoning tokens count as output tokens. Prompts over 272K tokens bill at $0.50 input and $1.875 output for the whole request, as at OpenAI.

Is there a cheaper GPT-6.1 Terra API?

Zurelay serves gpt-6.1-terra at 75% below OpenAI's list price, with the same model ID and request format. Cached input at $0.0125 per 1M lowers the cost further when your prompts share a long prefix. For simpler, high-volume tasks, GPT-6 Luna costs less per token.

How do I call the GPT-6.1 Terra API with the OpenAI SDK?

Install the official openai package and create a client with base_url set to https://api.zurelay.com/v1 and your Zurelay API key. Then send a Chat Completions request with model set to "gpt-6.1-terra". Set reasoning_effort to none, low, medium, high, xhigh or max, and cap output with max_completion_tokens. Only send temperature, top_p or logprobs when reasoning_effort is none.

What is the GPT-6.1 Terra context window?

GPT-6.1 Terra has a 1,050,000-token context window. One request can include up to 922,000 input tokens, and the model can write up to 128,000 output tokens. Input can be text, images or PDF files; output is text.

Can I use GPT-6.1 Terra for computer use on Zurelay?

OpenAI's built-in computer-use tool runs only through its Responses API, which Zurelay doesn't offer yet. On Zurelay's Chat Completions endpoint, Terra reads the screenshots you send as images and calls the tools you define with function calling, so you can drive a browser or desktop through your own tools.

GPT-6.1 Terra vs GPT-6.1 Sol: which should I use?

OpenAI lists Terra at half of Sol's price per token and says it finishes agent tasks over three times faster. For the most complex coding and agent work, OpenAI still recommends GPT-6.1 Sol. Terra also accepts reasoning effort none, which 6.1 Sol does not. Run both on a sample of your real prompts and pay for Sol only where it wins.

GPT-6.1 Terra vs GPT-5.6 Terra: what changed?

OpenAI's list price per token is half of GPT-5.6 Terra's. OpenAI reports that 6.1 Terra solved 50.3% of Terminal-Bench 4.0 tasks at maximum effort against 21.5%, cut the factual error rate at low effort from 53.6% to 16.7%, and has a later knowledge cutoff, June 1, 2026.

Does the GPT-6.1 Terra API support streaming, and what are the rate limits?

Yes. Set stream: true to receive tokens as they are generated, and add stream_options.include_usage to get token counts in the final chunk. You can give each Zurelay API key its own requests-per-minute limit and monthly budget in the dashboard. If an upstream call errors or times out, Zurelay retries it on another route before returning an error.

Is it the same GPT-6.1 Terra model OpenAI serves?

Yes. Requests to gpt-6.1-terra run on OpenAI's GPT-6.1 Terra. Zurelay doesn't swap in a smaller or cheaper model. Only smart routing, which you turn on yourself, can answer with a close alternative when the model is down, and the x-zurelay-model header names the model that answered. As with any call to OpenAI, two responses to the same prompt can differ because of sampling. Zurelay is independent and is not affiliated with or endorsed by OpenAI.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer