OpenAI: GPT-5.2-Codex
openai/gpt-5.2-codex
42nd smartest of 182ReasoningToolsJSONVision
Intelligence
40.1
42nd of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$1.75
262nd cheapest
Context
400K
128K max out
How it compares
Smarter than77%
of all ranked models
Cheaper than21%
of all ranked models
Overview
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis90th percentile
Intelligence Index
40.1
GPQA Diamond
90%
Humanity's Last Exam
34%
SciCode
55%
Tau²-Bench (agentic)
92%
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Azurecache | $1.75 | $14.00 | 400K | — |
Specifications
Context window400K
Max output128K
Knowledge cutoff—
Input modalitiestext, image
Output modalitiestext
Prompt cachingSupported
Cache read price$0.175/M
ModeratedNo
GPT-5.2-Codex FAQ
How much does GPT-5.2-Codex cost?
GPT-5.2-Codex costs $1.75 per million input tokens and $14.00 per million output tokens via OpenRouter, making it 262nd cheapest of 332 paid models.
How smart is GPT-5.2-Codex?
GPT-5.2-Codex scores 40.1 on the Artificial Analysis Intelligence Index, ranking 42nd of 182 benchmarked models, with a GPQA Diamond score of 90%.
What is GPT-5.2-Codex's context window?
GPT-5.2-Codex supports a 400K-token context window and can output up to 128K tokens. It accepts text, image input.