gpt-5-nano

OpenAI model performance over the last 24 hours.

Operational

Requests 24h10

Model avg latency 24h1.40s

Avg RPM 24h0.007

Avg TPM 24h0.600

Success rate 24h100.00%

Group	Requests 24h	Avg RPM 24h	Avg TPM 24h	Group avg latency 24h	Success rate 24h
default	10	0.007	0.600	1.40s	100.0%

Availability

Request success rate sampled in hourly windows over the last 24 hours. Grey points had no requests.

100%

99%

98%

97%

95%