LLM Reference

GPT-5.2 Codex

Released
2025-12-18
Last refreshed
2026-06-30
Status
Researched 17d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

GPT-5.2 Codex is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 400k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
GPT-5
Released
2025-12-18
Context
400k
Max output
128,000
Architecture
Decoder Only
Knowledge cutoff
2025-08
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$14.00
Input / 1M
$1.75

Cheapest of 2 routes · OpenAI API · cache read $0.175

About

GPT-5.2-Codex is OpenAI's agentic coding model built on GPT-5.2, released December 18, 2025. Optimized for long-horizon professional software engineering tasks including large refactors, multi-file changes, and codebase migrations. Features context compaction for handling tasks exceeding a single context window, enhanced vision for interpreting screenshots, diagrams, and UI, and strengthened safeguards for defensive cybersecurity workflows. Available to paid ChatGPT users and via the Responses API.

GPT-5.2 Codex is a proprietary model in the GPT-5 family. The structured metadata tracks a 400k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Vercel AI Gateway and OpenAI API, with the cheapest tracked route listed at $1.75 input and $14 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 72.8, SWE-bench Pro 56.4, and Terminal-Bench 2.0 64.0.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenAI API$1.75$14.00read $0.175
Serverless
Vercel AI Gateway$1.75$14.00read $0.175
Serverless

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt Caching

Benchmark peer barsfor Coding

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
SWE-bench Verified72.8SWE-bench Verified; mini-SWE-agent v2.0.0; attempts=1; % resolvedhttps://www.swebench.com/verified.html
SWE-bench Pro56.4SWE-Bench Pro Public; OpenAI launch comparison; GPT-5.2-Codex xhighhttps://openai.com/index/introducing-gpt-5-3-codex/
Terminal-Bench 2.064.0Terminal-Bench 2.0; OpenAI launch comparison; GPT-5.2-Codex xhighhttps://openai.com/index/introducing-gpt-5-3-codex/

Migration checks

No linked migration route is available for this model yet.

Compare GPT-5.2 Codex with other models

Show all 22 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of GPT-5.2 Codex?

GPT-5.2 Codex has a context window of 400k tokens.

What is the max output of GPT-5.2 Codex?

GPT-5.2 Codex can generate up to 128,000 output tokens.

How much does GPT-5.2 Codex cost?

GPT-5.2 Codex is available at $1.75/1M input tokens through Vercel AI Gateway.

When was GPT-5.2 Codex released?

GPT-5.2 Codex was released on 2025-12-18.

Which providers offer GPT-5.2 Codex?

GPT-5.2 Codex is available from 2 providers: Vercel AI Gateway, OpenAI API.

What benchmarks has GPT-5.2 Codex been tested on?

GPT-5.2 Codex has been evaluated on 3 benchmarks, including SWE-bench Verified, SWE-bench Pro, Terminal-Bench 2.0.