OpenAI
OpenAI's most efficient model for high-volume tasks.
Knowledge cutoff May 18, 2026. Reasoning can be disabled.
Latency
0.8s
Context
1.05M
Input
$0.05/M
Output
$0.10/M
{
"model": "gpt-6-luna",
"messages": [
{
"role": "user",
"content": "Hello, world."
}
]
}