← Model list

GPT-5.2 Codex

openai·openai/gpt-5.2-codex·GA·Closed·gpt-codex series

Code-specialist GPT for repository edits, reviews, and long-running software agents

At a glance
Reference price$2.19 / $17.50 per 1M
Cache read $0.219 · Venice AI
Lowest paid$0.14 / $1.14
QiHang Gateway · 15.6× spread
Context256,000
⚠ Providers report 256,000–400,000; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-08-31
Released / updated2025-12-11 / 2025-12-11

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier xhigh

Intelligence41.2
Value106
Coding
Agentic
Output speed
TTFT
Value formulaIQ 41.2 ÷ min blended $0.390 = 106

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 21 providers21 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
QiHangGateway$0.14$1.14400,000128,000
PoeGateway$1.60$13.00$0.16400,000128,000
OrcaRouterGateway$1.75$14.00$0.175400,000128,000
NanoGPTGateway$1.75$14.00$0.175400,000128,000
ImpossiblGateway$1.75$14.00$0.175400,000128,000
Jiekou.AIGateway$1.75$14.00400,000128,000
OpenRouterGateway$1.75$14.00$0.175400,000128,000
VivgridGateway$1.75$14.00$0.175400,000128,000
ZenMuxGateway$1.75$14.00$0.17400,00064,000
OfoxGateway$1.75$14.00$0.18400,000128,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1QiHang$85.00
2Poe$797.20
3ZenMux$860.40
4OrcaRouter$861.00
5NanoGPT$861.00
6Impossibl$861.00
The cheapest paid channel is the only channel.

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Prodataset: public41.04resolve rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

effort = loweffort = mediumeffort = higheffort = xhigheffort = noneeffort = minimal

6 / 21 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$17.50$02026-08-052026-08-132026-08-05 · Input list $2.192026-08-06 · Input list $2.192026-08-07 · Input list $2.192026-08-08 · Input list $2.192026-08-09 · Input list $2.192026-08-10 · Input list $2.192026-08-11 · Input list $2.192026-08-12 · Input list $2.192026-08-13 · Input list $2.192026-08-05 · Output list $17.502026-08-06 · Output list $17.502026-08-07 · Output list $17.502026-08-08 · Output list $17.502026-08-09 · Output list $17.502026-08-10 · Output list $17.502026-08-11 · Output list $17.502026-08-12 · Output list $17.502026-08-13 · Output list $17.502026-08-05 · Min blended $0.392026-08-06 · Min blended $0.392026-08-07 · Min blended $0.392026-08-08 · Min blended $0.392026-08-09 · Min blended $0.392026-08-10 · Min blended $0.392026-08-11 · Min blended $0.392026-08-12 · Min blended $0.392026-08-13 · Min blended $0.39