GPT-5.6 Luna
The fast, low-cost GPT-5.6, for high-volume work.
About GPT-5.6 Luna
GPT-5.6 Luna is the cheapest tier of the GPT-5.6 family, built for what OpenAI calls cost-sensitive, high-volume workloads. It is quick — independent measurements put it at about 178 tokens a second — and it scored 82.5% on Terminal-Bench 2.1, strong for the bottom tier of a family.
GPT-6 Luna has since replaced it with similar ability and newer knowledge, so this one is for products already running on it.
Where it’s strong
High-volume extraction and classification.
Light coding and command-line helper agents.
Products already built on GPT-5.6.
Where to be careful
Wordy: in one independent benchmark run it wrote about twice the median amount of output, and output is what you pay for.
Replaced by GPT-6 Luna, whose knowledge is three months newer.
Price
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $2.07 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.
Specs
gpt-5.6-lunaCall it
Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="gpt-5.6-luna",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Compare GPT-5.6 Luna
Questions
How much does GPT-5.6 Luna cost?
Input is $0.23 per 1M tokens; output is $1.38 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $2.07. The rate is published and does not change from one request to the next.
Can I use GPT-5.6 Luna alongside other models?
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from GPT-5.6 Luna to another model is a change to one word in your code.
Is GPT-5.6 Luna open source?
No. OpenAI does not publish the weights, so it is only available through an API like this one.