GPT-5.6 Luna is the fastest and lowest-cost model of OpenAI's GPT-5.6 series, released in July 2026. OpenAI built it for high-volume, latency-sensitive work such as chat, classification and lightweight agentic tasks, with enough reasoning for most routine requests. In Jantaris it has a 1,050,000-token context window and up to 128K output tokens. A few weeks after launch OpenAI lowered Luna's list price.
Best for
- Sorting and labeling large batches of text
- First-line answers in support chat
- Extracting fields from invoices, forms and emails
- Short summaries of long threads or logs
How to call it
The OpenAI SDK works as is, just set the Jantaris URL:
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-luna",
messages=[{"role": "user", "content": "Extract invoice number, date and total as JSON."}],
)
print(resp.choices[0].message.content)FAQ
How much does GPT-5.6 Luna cost in Jantaris?
$0.216 / $1.30 per 1M tokens. For short classification prompts that means you can process a large batch for very little, and you only pay for what you actually send.
Is GPT-5.6 Luna good enough for coding?
For small edits, snippets and explanations it is usually fine. For multi-file changes or debugging, use GPT-5.6 Terra or a Sol model, which OpenAI positions for heavier coding.
Does GPT-5.6 Luna support tool calls?
Yes. Pass function definitions in the OpenAI tools format and Jantaris returns the tool call for your code to run, as described in the chat endpoint docs. For extraction jobs, validate the returned fields in your code, since any model can occasionally skip one.
How to call GPT-5.6 Luna 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-luna",
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-luna", "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-luna",
messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);