modelbenchmark.io

GPT-5.2

openai-gpt-52

Compare

Reliable GPT generation for broad coding, writing, and tool-assisted product work

Specification

most-agreed values

Context
256K
Max output
66K
Released
2025-12-11
Knowledge cutoff
2025-08-31
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.75
Output
$14.00
Cache read
$0.175

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
venice$1.75$14.00$0.175—256K66K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02veniceCache read$0.219
2026-10-16veniceCache read$0.175
2026-09-02veniceInput$2.19
2026-10-16veniceInput$1.75
2026-09-02veniceOutput$17.50
2026-10-16veniceOutput$14.00

Other listings of this model

this page is one of them

The corpus files GPT-5.2 under several keys. This page is the openai-gpt-52 listing. The full record — every host, every price and every benchmark score — is on the main GPT-5.2 page.