OpenAIresponses

GPT-6.1 Terra API

GPT-6.1 Terra is OpenAI's balanced mid-tier model in the GPT-6.1 series, combining visual reasoning with fast, accurate computer operation.

The model supports text and image input with text output. It handles scoped code fixes, supports computer-use tasks with clearly defined outcomes, and is suited to agentic codebase investigation and iterative solution development. Everyday applications include drafting proposals, interpreting technical drawings, filling in forms, video editing, matching product photos with catalogs, and understanding complex documents.

At 16.1 seconds per task, it is reported as the fastest OpenAI model and the third fastest overall. Its error rate on error-inducing prompts at low reasoning effort is 16.7%, down from 53.6% for GPT-5.6 Terra. At max effort, the error rate is 4.3%. In the lineup, it sits below the flagship GPT-6.1 Sol and the top-tier GPT-6 Astra.

Open Playground ↗Create API Key ↗Getting started →

Updated: Oct 27, 2026

MODEL ID

gpt-6.1-terra

Context: 1.05M
Max output: 128K
Recommended API: responses
Input: file / image / text
Output: text

Highlights

Balanced mid-tier model in the GPT-6.1 series
Combines visual reasoning with accurate computer operation
16.1 seconds per task, reported fastest OpenAI model
Error rate 16.7% at low reasoning effort, down from 53.6%
Handles scoped code fixes and agentic codebase investigation

Providers

Best price

5 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details

$1	$5	$0.05
$1$0.3	$5$1.5	~~$0.05~~$0.015
$0.5	$2.5	$0.025
$1$0.6	$5$3	~~$0.05~~$0.03
$2	$10	$0.1

Pricing details

What $10 buys

Input: 10M tokens
Output: 2M tokens

Estimated from current input and output prices, before discounts.

Benchmarks

Error rate on error-inducing prompts (low reasoning effort)
Down from 53.6% for GPT-5.6 Terra
16.7%
Error rate on error-inducing prompts (max effort)
An 18-point improvement, roughly on par with GPT-6 Astra and GPT-6.1 Sol
4.3%
Unnamed benchmark score
OpenAI internal benchmark
78.2%

Scores as published by the model provider.

Reasoning

Default effort: medium
Enabled by default: Yes
Always enabled: No
Available effort levels: max / xhigh / high / medium / low / none

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open Playground Create API Key

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

gpt-6.1-terra

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/responses", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "gpt-6.1-terra",
  "input": "Hello"
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/responses \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.1-terra",
  "input": "Hello",
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Responses

Responses-compatible agent and workflow requests.

POST

https://openapi.felo.ai/api/v1/responses

Parameters

NameTypeDefaultDescription

modelstringgpt-6.1-terraPublic model ID to call.

inputstring | array——

include_reasoning———

max_tokensinteger—Maximum generated tokens.

reasoning———

reasoning_effort———

response_formatobject—Request structured output when supported.

seed———

structured_outputs———

tool_choicestring or object—Controls whether a tool should be called.

toolsarray—Tool calling definitions following compatible schema.

verbosity———

Frequently asked questions

What is GPT-6.1 Terra?

GPT-6.1 Terra is a mid-tier model in OpenAI's three-tier GPT-6.1 series, positioned between the flagship GPT-6.1 Sol and the fast, low-cost GPT-6.1 Luna. It combines detailed visual reasoning with accurate computer operation and writes clearer, more natural prose. Announced and made available on October 26, 2026, through ChatGPT Work, Codex, and the API, it is designed as a fast and efficient option for everyday professional work. The model supports text and image input with text output. It handles scoped code fixes, supports computer-use tasks with clearly defined outcomes, and is suited to agentic codebase investigation and iterative solution development. Everyday applications include drafting proposals, interpreting technical drawings, filling in forms, video editing, matching product photos with catalogs, and understanding complex documents. At 16.1 seconds per task, it is reported as the fastest OpenAI model and the third fastest overall. Its error rate on error-inducing prompts at low reasoning effort is 16.7%, down from 53.6% for GPT-5.6 Terra. At max effort, the error rate is 4.3%. In the lineup, it sits below the flagship GPT-6.1 Sol and the top-tier GPT-6 Astra.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

OpenAIgpt-6-luna

GPT-6 Luna is OpenAI's fast, affordable model for high-volume reasoning and knowledge work, with a 1,050,000-token context and flexible reasoning controls.

high-volume reasoning taskswriting and summarizationlong-context document analysiscomputer-use scenarios

Context

1.05M

Max output

128K

Input tokens · Base rate

$0.1 / 1M tokens

Output tokens · Base rate

$0.5 / 1M tokens