GPT-6 Sol API

GPT-6 Sol is the mid-to-high tier of OpenAI's GPT-6 family, released in September 2026. It sits below the flagship GPT-6 Astra and above the fast GPT-6 Luna. OpenAI says Sol and Luna were trained with methods similar to Astra's, to bring those gains to cheaper, faster models. In Jantaris, GPT-6 Sol has a 1,050,000-token context window and up to 128K output tokens. OpenAI pitches it for difficult work tasks where you want to iterate many times without paying flagship rates.

Best for

• Complex analysis and reasoning over long documents
• Coding and agent workflows that need many iterations
• A default high-quality model for internal tools
• Replacing GPT-5.6 Sol in existing OpenAI code

How to call it

If you already use the OpenAI SDK, change only base_url and the key:

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gpt-6-sol",
    messages=[{"role": "user", "content": "Compare these two vendor contracts clause by clause."}],
)
print(resp.choices[0].message.content)

FAQ

What is the GPT-6 Sol API price?

Jantaris charges $2.16 / $10.80 per 1M tokens. You see the rate before sending anything, and usage is deducted from a balance that does not expire.

How big is the GPT-6 Sol context window?

1,050,000 tokens in Jantaris, with replies up to 128K tokens. That is enough for a large codebase or several hundred pages of text in a single call, though long prompts cost more, so trim what the model does not need.

Should I use GPT-6 Sol or GPT-6 Astra?

OpenAI says Astra is its best model across the board, while Sol handles difficult tasks at a lower cost. Build and test on Sol first, then switch the model field to GPT-6 Astra for the cases where Sol's answers are not good enough. No other code changes are needed.

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