OGPT-5.2-CodexAPI

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.

400KContext window · tokens

$1.75Input price · per M tokens

$14Output price · per M tokens

OpenAIProvider

Prices update automatically — checked daily against provider list prices.

$4.81 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
cheaper than 25% of the 192 commercial models tracked here
64 of 88 OpenAI models tracked here, from cheapest

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for GPT-5.2-Codex, measured by Artificial Analysis. Higher is better. Measurement mode: xhigh.

Intelligence index41.2

GPQA89.9%

Humanity's Last Exam35.7%

Long Context Reasoning79.3%

SciCode54.6%

IFBench77.6%

τ²-Bench92.1%

Terminal-Bench Hard37.1%

💰 Blended price$4.813 / 1M tokens

📈 Value8.6 intelligence points per $

vs. models measured heretop 24%

Scores higher than 76% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.74 per 1M tokens (median of 17) — this one costs $4.81.
Cheaper and better on this index: GPT-5.6 Sol · Grok 4.6 · GPT-5.6 Sol (batch) and 40 more

Benchmark data by Artificial Analysis

About this model

GPT-5.2-Codex is a commercial AI model by OpenAI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is GPT-5.2-Codex?

GPT-5.2-Codex is an AI language model from OpenAI. It is a proprietary model, available through an API. It scores 41.2 on the Artificial Analysis intelligence index.

Is GPT-5.2-Codex free?

GPT-5.2-Codex is not free: it costs $1.75 per million input tokens and $14 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is GPT-5.2-Codex good at?

Independent benchmarks from Artificial Analysis give it GPQA 89.9%, Humanity's Last Exam 35.7%, Long Context Reasoning 79.3%, SciCode 54.6%, IFBench 77.6%, τ²-Bench 92.1%, Terminal-Bench Hard 37.1%.