gpt-5.2
List prices per 1M tokens, what provider caching gives back, and what the cheaper sibling costs for the same work.
$1.75input / 1M
$14output / 1M
$0.175cached input / 1M (90% off)
nonecache write / 1M (no write surcharge)
Same workload, cheaper sibling
100k requests/month of 2,000 input (1,500 static) and 300 output tokens, at list prices. "With cache" assumes the static prefix is served from the provider cache.
| Model | Per request | Per month | With cache | vs gpt-5.2 |
|---|---|---|---|---|
| gpt-5.2 (this model) | $0.0077 | $770 | $533.75 | — |
| gpt-5-mini | $0.0010999999999999998 | $110 | $76.25 | 85.7% |
List prices. Cheaper models need an eval before swapping; TokenZero cascade routing is opt-in and advisory by default; an opt-in shadow parity monitor is coming.
Use it through TokenZero
OPENAI_BASE_URL=https://tokenzero.sh/v1 # keep your own key; cache formatting on, routing advisory
Free up to $500/month of routed spend; paid plans are a share of verified savings (Pro Cap: never more than $199/mo). Pricing