GPT-5.2 Codex

GPT-5.2 Codex is OpenAI's latest entry in its specialist coding model family, positioned as a version of GPT-5.2 that has been further refined for agentic coding inside the Codex environment. OpenAI describes it as the most advanced agentic coding model it has released for complex, real-world software engineering, with particular emphasis on professional development workflows. The model sits within the GPT-X Codex lineage of specialist coding models and is distinct from OpenAI's Codex CLI and Codex Cloud coding-agent tools, which are separate products that sit on top of these models.

The reported improvements focus on four areas: long-horizon task handling through context compaction, which helps the model stay effective across extended agentic sessions; stronger performance on large-scale code changes such as refactors and migrations; better behavior in Windows development environments; and significantly stronger cybersecurity capabilities, which OpenAI frames as part of its broader cyber-resilience work rather than a separately trained skill set. In practice, these gains make the model a good fit for teams running long-running coding agents that need to plan, edit, and verify substantial changes across a codebase, with particular advantages on Windows-centric projects and security-sensitive engineering tasks.

DevPass (LLM Gateway)gpt-5.2-codexgpt-codex

Open provider page Provider docs

Quick Info

Provider: DevPass (LLM Gateway)
Model key: gpt-5.2-codex
Release date: Dec 11, 2025
Last updated: Dec 11, 2025
Knowledge cutoff: 2025-08-31
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $1.75
Output token cost: $14.00

Limits

Input tokens: 272,000 tokens
Output tokens: 128,000 tokens
Context window: 400,000 tokens

Transparent token rates

Compare GPT-5.2 Codex pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT-5.2 Codex

Abacus

CoverageBenchmark

This Magica model directory page lists GPT-5.2-Codex as developed by OpenAI with a context window of 400K tokens, an output limit of 128K tokens, and a release date of January 14, 2026. The page reports pricing at $1.75 per million input tokens, $14.00 per million output tokens, $0.01 per web search, and $0.175 per mil The page also reports a Best Design Arena Score of 1,176 Elo, placing GPT-5.2-Codex 19th in the Android Native category with a 47.5% win rate, sourced from arena comparisons. According to the supplied excerpt, the page includes comparison widgets pairing GPT-5.2-Codex against models such as GPT-5.6 Luna, GLM 5.3 Flash,

OrcaRouter

Coverage

A third-party model registry entry for GPT-5.2 Codex lists it as a closed-source, proprietary dense model with a 400K context length, text modality, and a stated July 2025 knowledge cutoff. It frames the model as specialized for autonomous multi-file refactoring, visual UI debugging, and secure system design, with pers The same page reports LiveBench category scores including Coding 0.84, Data Analysis 0.78, Global 0.74, Agentic Coding 0.49, Mathematics 0.89, Average 0.74, Reasoning 0.78, and a WebDev Arena score of 1338, giving an overall rank of 84 and a Coding rank of 37. These benchmark figures have unverified provenance and meth