Inference Space

GPT-5.6 Luna

GPT

Latency & token rates

TTFT (p50)

10,012ms
p50 latency, last 7d

p50 latency, last 7d

Input token rate

5,266token/s

Output token rate

28token/s

Traffic & availability

Requests, 7d

43,633

Requests, 30d

178,202

98.01% uptime over the trailing 7 days.

Availability

98.01%

7d uptime

OperationalDegradedOutage