GPT-5.6 Terra

GPT-5.6 Terra is the sensible default for daily work when Sol would be more model than the task needs. OpenAI released it in July 2026 as the middle tier of GPT-5.6, between the flagship Sol and the budget Luna, and said at launch that it performs about as well as GPT-5.5 for less money.

OpenAI recommends it for everyday coding, reasoning and agent tasks.

What you can use it for

• Coding help inside your editor
• Business chat assistants that need solid reasoning
• Agents with a handful of tools and clear instructions
• Rewriting, translating and restructuring documents
• A cheaper first stop before you escalate to Sol

Settings and limits

• Context window: 1,050,000 tokens; output up to 128K tokens.
• Streaming: pass stream=True and the answer arrives as it is written, same as with the OpenAI API. See the chat endpoint docs.
• Each response carries a usage field with input and output tokens. That is exactly what you pay for, so log it to learn the real cost of a typical task.
• A simple routing rule: Terra by default, GPT-5.6 Sol only for the hard cases.

Example request

from openai import OpenAI

client = OpenAI(
    base_url="https://kadraris.com/v1",
    api_key="sk-kd-...",
)
resp = client.chat.completions.create(
    model="gpt-5.6-terra",
    stream=True,
    messages=[{"role": "user",
               "content": "Turn these meeting notes into "
                          "a task list with owners."}],
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

Paste your notes under the instruction and name the output format you want.

Questions

What does GPT-5.6 Terra cost?

$2.16 / $12.96 per 1M tokens on Kadraris. A failed request costs $0.

How do Sol, Terra and Luna differ?

Sol is the most capable and the priciest, Luna the fastest and cheapest, Terra in between. GPT-5.6 Luna handles simple high-volume jobs well.

Which GPT-6 model is closest?

Kadraris offers Astra, Sol and Luna from GPT-6. For a newer mid-to-high tier, try GPT-6 Sol.

GPT-5.6 Terra in your code

from openai import OpenAI

client = OpenAI(base_url="https://kadraris.com/v1", api_key="sk-kd-...")
resp = client.chat.completions.create(
    model="gpt-5.6-terra",
    messages=[{"role": "user", "content": "Suggest three opening shots for a short film about a cafe."}],
)
print(resp.choices[0].message.content)

curl https://kadraris.com/v1/chat/completions \
  -H "Authorization: Bearer $KADRARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5.6-terra", "messages": [{"role": "user", "content": "Suggest three opening shots for a short film about a cafe."}]}'

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://kadraris.com/v1", apiKey: process.env.KADRARIS_API_KEY });
const resp = await client.chat.completions.create({
  model: "gpt-5.6-terra",
  messages: [{ role: "user", content: "Suggest three opening shots for a short film about a cafe." }],
});
console.log(resp.choices[0].message.content);