Loading
Loading
Model record / OpenAI
Access gpt-realtime-2 from OpenAI through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
See how much this model saves and when its recorded price has been lowest.
Savings are visible now, but a best-time recommendation needs at least 12 observations across 6 different hours.
Average saved
0.0%
Cheapest time
Collecting data
Hourly coverage
1/24
Signal quality
Early
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
—
of 348 ranked models
Last 7 days
—
of 370 ranked models
Last 30 days
—
of 370 ranked models
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/realtime
websocat -H "Authorization: Bearer ci_live_YOUR_API_KEY" "wss://api.cheaperinference.com/v1/realtime?model=gpt-realtime-2"{"type":"session-update","config":{"instructions":"Answer in one word."}}{"type":"conversation-item-create","item":{"type":"text-message","role":"user","text":"Reply with the single word OK."}}{"type":"response-create"}