GPT-6.1 Terra API

GPT-6.1 Terra is the faster, cheaper model in OpenAI's GPT-6.1 series, aimed at writing and visual reasoning. It takes text and images, has a 1,050,000-token context and six reasoning_effort levels (default medium). It supports JSON schema output. Per token it costs less than GPT-6.1 Sol.

Billing note: according to the docs, max_completion_tokens is currently not enforced on this model (a 40-token cap returned about 480 tokens). Control length in the prompt and with a lower reasoning_effort.

Best for

• Marketing copy, emails and product descriptions in bulk
• Describing and analysing photos, screenshots and scanned documents
• Assistants and chats where speed matters
• First drafts that a stronger model polishes later

How to call it

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gpt-6.1-terra",
    reasoning_effort="low",
    messages=[{"role": "user", "content": "Write three short variants of this product description, max 40 words each."}],
)
print(resp.choices[0].message.content)

FAQ

What is the GPT-6.1 Terra API price?

$1.01 / $5.06 per 1M tokens. Prompts over 272K input tokens are billed at the long-context rate.

Can I cap the answer length?

max_completion_tokens is currently ignored upstream. State the limit in the prompt (e.g. "max 100 words") and set reasoning_effort to low.

Terra or Sol?

Terra for fast writing and image tasks, GPT-6.1 Sol for hard code and long analysis.

How to call GPT-6.1 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-6.1-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-6.1-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-6.1-terra",
  messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);