GPT-5.2 Codex

GPT-5.2 Codex is a member of OpenAI's Codex family of agentic coding models, positioned as the immediate predecessor to GPT-5.3-Codex. Its successor announcement explicitly credits GPT-5.2-Codex with delivering the frontier coding performance that GPT-5.3-Codex builds upon, combining the coding strengths of the Codex line with the broader reasoning and professional knowledge capabilities of the base GPT-5.2 model. This lineage places the model squarely inside OpenAI's push toward longer-running, tool-using software engineering agents that can plan, execute, and iterate across complex development tasks.

OpenAI framed the Codex family as capable of taking on research, tool use, and complex execution in a single workflow, with the successor model noted as 25% faster while retaining the careful, methodical debugging style that community discussion associates with the GPT-5.x Codex line. Practical fit centers on agentic software engineering work: multi-step code generation, codebase navigation, and structured tool-driven tasks where reasoning and steady execution matter more than raw throughput. With a newer Codex generation now available, GPT-5.2 Codex remains relevant for teams standardizing on a known-good Codex checkpoint or routing through compatible gateways that still serve this version.

Kilo Gatewayopenai/gpt-5.2-codexgpt-codex

Open provider page Provider docs

Quick Info

Provider: Kilo Gateway
Model key: openai/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