OpenAI · all models ›

OGPT-5 Codex (batch)API

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows.

400KContext window · tokens
$0.63Input price · per M tokens
$5Output price · per M tokens
OpenAIProvider

Prices update automatically — checked daily against provider list prices.

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for GPT-5 Codex (batch), measured by Artificial Analysis. Higher is better. Measurement mode: high.

Intelligence index37
Math index98.7
GPQA83.7%
MMLU-Pro86.5%
Humanity's Last Exam27.8%
Long Context Reasoning71%
LiveCodeBench84%
SciCode40.9%
AIME 202598.7%
IFBench74.1%
τ²-Bench86.8%
Terminal-Bench Hard37.9%
💰 Blended price$3.438 / 1M tokens
📈 Value10.8 intelligence points per $
vs. models measured heretop 35%
Scores higher than 65% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $1.72 per 1M tokens (median of 27) — this one costs $1.72.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 37 more
Benchmark data by Artificial Analysis

About this model

GPT-5 Codex (batch) is a commercial AI model by OpenAI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is GPT-5 Codex (batch)?

GPT-5 Codex (batch) is an AI language model from OpenAI. It is a proprietary model, available through an API. It scores 37 on the Artificial Analysis intelligence index.

Is GPT-5 Codex (batch) free?

GPT-5 Codex (batch) is not free: it costs $0.63 per million input tokens and $5 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is GPT-5 Codex (batch) good at?

Independent benchmarks from Artificial Analysis give it GPQA 83.7%, MMLU-Pro 86.5%, Humanity's Last Exam 27.8%, Long Context Reasoning 71%, LiveCodeBench 84%, SciCode 40.9%, AIME 2025 98.7%, IFBench 74.1%, τ²-Bench 86.8%, Terminal-Bench Hard 37.9%. It is particularly used for mathematical reasoning.

Related models

o1-proOpenAIo1-pro (batch)OpenAIGPT-5.5 ProOpenAIGPT-5.4 ProOpenAIGPT-5.2 ProOpenAIGPT-5 ProOpenAI