Loading
LoadingModel record / OpenAI
Access gpt-5.2-codex from OpenAI through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Observed reliability
84.3
Output speed
—
This model averaged 27.5% below comparable direct provider prices across the selected range. Its strongest observed window was 11:00 PM–1:00 AM in UTC.
Average saved
27.5%
Cheapest time
11:00 PM–1:00 AM
Hourly coverage
24/24
Signal quality
High
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#40
of 60 ranked models
Last 7 days
#55
of 60 ranked models
Last 30 days
#59
of 60 ranked models
p95 latency
33,425
Evidence strength
—
curl https://api.cheaperinference.com/v1/chat/completions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.2-codex", "messages": [{"role": "user", "content": "Hello!"}] }'