All Models
OpenAIFrontierNew

GPT-5.2 Codex

Specialized code generation model optimized for software engineering tasks. Superior at code completion, debugging, refactoring, and multi-file editing.

4.7(8,200 ratings)

Quick Overview

CategoryCode
Context Window256K tokens
SpeedStandard
Input$12 / 1M tokens
Output$48 / 1M tokens

Pricing

Simple, transparent token-based pricing. Pay only for what you use.

Input Tokens
$12
per 1M tokens
Output Tokens
$48
per 1M tokens

Capabilities

Core strengths and supported features of GPT-5.2 Codex.

Code Generation
Debugging
Refactoring
Code Review

Performance

Context window capacity and inference speed characteristics.

Context Window

256K

Extended context window suitable for processing long documents, large codebases, and multi-turn conversations with extensive history.

Speed: Standard

Balanced speed and quality. Well-suited for production workloads that need a good balance between response quality and latency.

Quick Start

Get started with GPT-5.2 Codex in just a few lines of code.

import OriginalPoint from "originalpoint";

const client = new OriginalPoint({
  apiKey: process.env.ORIGINALPOINT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-5.2-codex",
  messages: [
    {
      role: "user",
      content: "Hello, how can you help me today?",
    },
  ],
  max_tokens: 1024,
});

console.log(response.choices[0].message.content);

More from OpenAI

Explore other models available from OpenAI.

GPT-5.4

Frontier

Most advanced reasoning model from OpenAI. Excels at complex multi-step tasks, code generation, and nuanced analysis with state-of-the-art performance across all benchmarks.

256K contextFrom $15/1M4.8

GPT-4o

Frontier

Multimodal model with strong performance at an accessible price point. Processes text, images, and audio with fast response times.

128K contextFrom $3/1M4.6

GPT-4o Mini

Economy

Cost-efficient model for lightweight tasks. Ideal for classification, extraction, summarization, and simple conversational AI applications.

128K contextFrom $0.15/1M4.3

o3

Frontier

Advanced reasoning model that uses chain-of-thought to solve complex problems. Excels in mathematics, science, and logical reasoning with verifiable step-by-step explanations.

200K contextFrom $10/1M4.9

o3 Mini

Balanced

Efficient reasoning model that balances chain-of-thought capabilities with speed. Good for tasks requiring structured thinking at a lower cost.

200K contextFrom $1/1M4.4