GPT-6 Astra API

GPT-6 Astra is the flagship of OpenAI's GPT-6 family and the first model of that generation, available in Jantaris since September 2026. It has a 1,050,000-token context window and up to 128K output tokens. OpenAI calls it its best model across the board and names software engineering, computer use, browsing, cybersecurity, science and professional work as its strong areas. In Codex, OpenAI says Astra can keep notes across context windows during long jobs instead of squeezing everything into one summary.

Best for

• Deep research that combines many sources into one report
• End-to-end software engineering tasks with long horizons
• Scientific and technical analysis where accuracy matters most
• Document creation from large, messy inputs
• A final check on answers produced by cheaper models

How to call it

Point the OpenAI SDK at Jantaris:

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "Design a test plan for this payments service."}],
)
print(resp.choices[0].message.content)

FAQ

How much does GPT-6 Astra cost?

In Jantaris: $10.80 / $54.00 per 1M tokens. It is the top price tier among OpenAI models, so it pays off on tasks where a better answer saves hours of human work.

When is Astra worth the price over GPT-6 Sol?

When GPT-6 Sol fails on your hardest cases. A common pattern is to send most traffic to Sol and route only the difficult requests to Astra. With one Jantaris key both models share the same balance and code path.

How do I keep GPT-6 Astra costs under control?

Create a separate API key for Astra and set a monthly spend limit on it in the dashboard. Also trim long prompts: with a 1.05M-token window it is easy to send far more context than the task needs, and every input token is billed.

How to call GPT-6 Astra 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-astra",
    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-astra", "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-astra",
  messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);