openai

OpenAI: GPT-5 Codex (batch)

The OpenAI GPT-5 Codex (batch) is designed for handling both text and image inputs with a context length of 400,000 tokens and supports reasoning, making it suitable for complex tasks that require understanding across large volumes of data or visual content. It can process multi-modal inputs and engage in detailed reasoning but does not offer structured output capabilities. Given its high price point at $5.00 per million output tokens and $0.625 per million input tokens, the GPT-5 Codex is best suited for organizations willing to invest in premium AI solutions that can handle extensive reasoning tasks with text and images. However, due to a lack of independent benchmark coverage, its performance relative to other models remains unproven, making it essential to carefully consider alternative options before shortlisting this model.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.62
per 1M tokens
Output Price
$5.00
per 1M tokens
Context Window
400,000
tokens
Model ID
openai/gpt-5-codex:batch
Vendor
openai
Released
September 2025
Tokenizer
GPT
Input Modalities
text, image
Output Modalities
text
Max Output
128,000 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
yes

What it costs in practice

Computed from the current $0.62/M input and $5.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.03
Classify 1,000 customer emails 500k in / 50k out $0.56
A month of a busy support chatbot 5M in / 2M out $13.12

Similar models

Quick answers

How much does OpenAI: GPT-5 Codex (batch) cost?
$0.62 per million input tokens and $5.00 per million output tokens.
What is OpenAI: GPT-5 Codex (batch)'s context window?
400,000 tokens, roughly 600 pages of text in a single request.
Does OpenAI: GPT-5 Codex (batch) support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can OpenAI: GPT-5 Codex (batch) process images?
Yes, it accepts image input.