GPT-6.1 Terra

Last updated: 27 October 2026. Official prices and limits from OpenAI's GPT-6.1 Terra model page.

GPT-6.1 Terra vs GPT-6.1 Sol, Astra, and Luna

OpenAI describes GPT-6.1 Terra as a model for visual reasoning, precise computer use, and clear, natural writing. On price it sits between GPT-6.1 Sol and GPT-6 Luna: input, output, and cached input all cost exactly half of Sol's rates, and a fraction of Astra's.

Prices below are per 1M tokens. The AIReiter columns are what you pay here.

Key specs

• Context: a 1,050,000-token context window, up to 922K input tokens and 128K output tokens.
• Modalities: text and image in, text out. Audio and video are not supported.
• Reasoning effort: none, low, medium (default), high, xhigh, and max.
• Long context: requests above 272K input tokens are billed at 2x input and cache rates and 1.5x output for the whole request.
• Knowledge cutoff: 1 June 2026.

Which one to pick

Against its predecessor GPT-5.6 Terra, the official price halves on input and drops from $12 to $5 on output. Use Luna for routine, high-volume traffic such as classification and extraction. Use GPT-6.1 Terra for screenshot and chart understanding, computer-use agents, and writing that has to read naturally. Escalate to GPT-6.1 Sol or Astra only where Terra measurably falls short on your own evaluations.

Call GPT-6.1 Terra from your code

The endpoint is OpenAI-compatible, so existing OpenAI clients work by changing the base URL and the API key. The model ID is gpt-6.1-terra.

Tool calling works on both endpoints. On OpenAI's own API, GPT-6.1 Terra requires the Responses API for tool calling. On AIReiter, Chat Completions requests with tools are handled for you, so existing tool loops keep working after you switch the model ID. New integrations can use either /api/v1/chat/completions or /api/v1/responses.

curl (Chat Completions with an image)

curl https://aireiter.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AIREITER_API_KEY" \
  -d '{
    "model": "gpt-6.1-terra",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What does this chart show? Answer in two sentences."},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}}
      ]
    }],
    "reasoning_effort": "medium"
  }'

Python with tool calling (Responses API)

from openai import OpenAI

client = OpenAI(
    base_url="https://aireiter.com/api/v1",
    api_key="YOUR_AIREITER_API_KEY",
)

response = client.responses.create(
    model="gpt-6.1-terra",
    input="What is the weather in Paris right now?",
    reasoning={"effort": "low"},
    tools=[{
        "type": "function",
        "name": "get_weather",
        "description": "Get the current weather for a city.",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    }],
)

for item in response.output:
    if item.type == "function_call":
        print(item.name, item.arguments)

Node (Chat Completions, streaming)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://aireiter.com/api/v1",
  apiKey: process.env.AIREITER_API_KEY,
})

const stream = await client.chat.completions.create({
  model: "gpt-6.1-terra",
  messages: [{ role: "user", content: "Rewrite this release note so it reads naturally: ..." }],
  reasoning_effort: "none",
  stream: true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

Use GPT-6.1 Terra in Codex CLI

Codex CLI talks to the Responses API, so tool use works out of the box. Put this in ~/.codex/config.toml, then export your key as AIREITER_API_KEY:

model_provider = "aireiter"
model = "gpt-6.1-terra"
model_reasoning_effort = "medium"
disable_response_storage = true

[model_providers.aireiter]
name = "AIReiter"
base_url = "https://aireiter.com/api/v1"
wire_api = "responses"
env_key = "AIREITER_API_KEY"

base_url must stop at /api/v1. Keep the real key in the environment variable, never in the TOML file. Grab a key on the API keys page and see the LLM API integration guide for other clients.

What GPT-6.1 Terra actually costs you

Here is the arithmetic on three realistic workloads at AIReiter's rate of $0.30 input and $1.50 output per 1M tokens, with no cache hits.

• Cached input reads cost $0.015 per 1M, one twentieth of a fresh read. If 40K of that 50K agent step is a cached prefix, the step drops from $21.00 to $9.60 per 1,000 requests. Cache writes cost $0.375 per 1M.
• Requests above 272K input tokens are surcharged for the whole request, at 2x on input and cache and 1.5x on output. A 300K-in / 4K-out request costs about $0.189, while the same task trimmed to 270K costs about $0.087.

Output tokens cost five times what input tokens cost. Higher reasoning effort produces more reasoning tokens, which are billed as output, so use none or low for rewriting and quick answers and save xhigh and max for hard problems.