GPT-5.3 Codex
GPT
Latency & token rates
Live latency and token rates require platform integration. They will appear here once a platform key is configured.
Traffic & availability
Requests, 7d
—
Requests, 30d
120,036
100.00% uptime over the trailing 7 days.
Availability
100.00%
7d uptime
OperationalDegradedOutage