| gpt-5.6-luna | gpt-6-luna | |
|---|---|---|
| Providers | OpenAI | OpenAI |
| Input $/M | $0.20 | $0.10 |
| Output $/M | $1.20 | $0.50 |
| Output multiplier | ×6.00 | ×5.00 |
| Context window | 1.05M tokens | 1.05M tokens |
| Intelligence index | 43.4 | — |
| Coding index | 71.4 | — |
gpt-6-luna is roughly 2.0× cheaper on input than gpt-5.6-luna. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to gpt-5.6-luna deliberately rather than by default.
Tags: gpt-5.6-luna — Chat, Reasoning, Coding, Vision · gpt-6-luna — Chat, Reasoning, Coding, Vision
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# gpt-5.6-luna
client.chat.completions.create(model="gpt-5.6-luna", messages=[{"role":"user","content":"Hi"}])
# gpt-6-luna
client.chat.completions.create(model="gpt-6-luna", messages=[{"role": "user", "content": "Hi"}])