Skip to model information

codex-mini-latest

Retired

An OpenAI model with a 200K-token context window, image input and tool calling. Released on the OpenAI API May 16, 2025, now retired.

Access details: OpenAI API

An alias. The provider can point it at a newer version.

codex-mini-latest
Updated Sep 23, 2026

Capabilities & limits

Context window
200K
Maximum output
100K
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
No longer sold
Output
No longer sold

No longer sold on the OpenAI API.

Price history
Feb 12, 2026

Input No longer sold per million tokens

Feb 12, 2026

Output No longer sold per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
Jun 01, 2024
Input modalities
Text, image
Output modalities
Text

Release & lifecycle

First available
May 16, 2025
deprecated
As of Sep 13, 2026
retired
As of Sep 23, 2026

Considering a switch?

Specs only go so far. Try both on your own tasks and compare quality, speed and cost.

Compare with Gemini 2.5 Pro →

Prices and availability as of October 20, 2026. OpenAI's own pages have the latest.