GPT-5.6 Terra is the middle tier of OpenAI's GPT-5.6 series, released in July 2026. It sits between the flagship Sol and the low-cost Luna and aims for a balance of capability, speed and price. At launch OpenAI said Terra performs about as well as GPT-5.5 at a lower price. In Jantaris it has a 1,050,000-token context window and up to 128K output tokens. OpenAI recommends it for everyday coding, reasoning and agentic work where Sol would be more than you need.
Best for
- Everyday coding help in the editor
- Business chat assistants that need solid reasoning
- Agents with moderate tool use and clear instructions
- Rewriting, translating and structuring documents
- A cheaper default before escalating to Sol
How to call it
Swap the base URL in the OpenAI SDK:
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="gpt-5.6-terra",
messages=[{"role": "user", "content": "Turn these meeting notes into action items with owners."}],
)
print(resp.choices[0].message.content)FAQ
What is GPT-5.6 Terra's price per million tokens?
Jantaris bills $2.16 / $12.96 per 1M tokens. Each response includes a usage field with input and output tokens, which is exactly what you are charged for, so you can log the real cost of a typical task.
How is Terra different from Sol and Luna?
Sol is the most capable and most expensive of the three, Luna the fastest and cheapest, and Terra sits between them. A simple setup is to send routine requests to Terra and escalate only the hard ones to GPT-5.6 Sol.
Does GPT-5.6 Terra support streaming?
Yes. Pass stream=True to client.chat.completions.create and Jantaris returns the answer as it is generated, the same way the OpenAI API does. Details are in the chat endpoint docs.
How to call GPT-5.6 Terra via API
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="gpt-5.6-terra",
messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)curl https://jantaris.com/v1/chat/completions \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.6-terra", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
model: "gpt-5.6-terra",
messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);