GPT-5.2-Codex

Tool callingStructured outputReasoningImage inputFile input

Launch post Website Docs

Code-specialist GPT for repository edits, reviews, and long-running software agents

Context: 400K
Released: 10mo ago
Input / 1M tokens: $1.75
Output / 1M tokens: $14.00
Cached input / 1M tokens: $0.18

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
Terminal Bench	66.5% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.2-codex Agent: Deep Agents https://www.tbench.ai/leaderboard/terminal-bench/2.0 Original-source terms apply

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: OpenAI
Model family: GPT
Type: Language model
Predecessor: —
Successor: —
Released: December 11, 2025
Model ID: openai/gpt-5.2-codex
Openness: Closed
License: —
Input modalities: text, image
Output modalities: text
Modality: text+image->text
Tokenizer: GPT
Max output tokens: 128K
Knowledge cutoff: 2025-08-31
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: openai/gpt-5.2-codex
Source family: gpt-codex
Last updated: 2025-12-11
Knowledge cutoff: 2025-08-31
Model context: 400K
Maximum input: 272K
Model output limit: 128K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: No

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Pro	41.04 · resolve rate	public	Source

Complete source record (JSON)

{
  "id": "openai/gpt-5.2-codex",
  "name": "GPT-5.2 Codex",
  "description": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
  "family": "gpt-codex",
  "last_updated": "2025-12-11",
  "knowledge": "2025-08-31",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": false,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 400000,
    "input": 272000,
    "output": 128000
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Pro",
      "score": 41.04,
      "source": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
      "metric": "resolve rate",
      "dataset": "public"
    }
  ],
  "release_date": "2025-12-11",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Azure	azure	400K	$1.75	$14.00	$0.18	—	98.95%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation