GPT 5.6 Luna
$0.027286% offper 1M tokens$0.286% off
The fast, cost-efficient model in GPT-5.6. It suits high-volume, latency-sensitive tasks like chat, classification, and lightweight agent work.
1.05MContext
$0.0272Input / 1M
$0.163Output / 1M
86%Saved vs retail
client.chat.completions.create( model="gpt-5-6-luna", messages=[ {"role": "user", "content": "Hello"}, ],)
Cost per 1M input tokens
Studios$0.0272
Retail$0.2