Skip to model information

GPT-5.3-Codex

Deprecated

An OpenAI model with a 400K-token context window, image input and tool calling. On the OpenAI API since February 24, 2026, now deprecated.

Access details: OpenAI API

The model ID to use in API requests.

gpt-5.3-codex
Updated Sep 23, 2026

Capabilities & limits

Context window
400K
Maximum output
128K
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$1.75
Output
$14.00

Standard rates per million tokens. Discounts and long-context rates, where offered, are on OpenAI's pricing page.

Full rate card 3 rates

All prices in USD.

Standard input

$1.75 per 1M tokens

Standard output

$14.00 per 1M tokens

Cached input

$0.175 per 1M tokens

Listed in the pricing page specialized models table (Codex category); no Batch, Flex or Fast rates are listed for it.

Price history
Sep 23, 2026

Input $1.75 per million tokens

Sep 23, 2026

Output $14.00 per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
Aug 31, 2025
Input modalities
Text, image
Output modalities
Text

Release & lifecycle

First available
Feb 24, 2026
available
As of Sep 23, 2026
deprecated
As of Oct 20, 2026

Considering a switch?

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

Compare with Kimi K2.7 Code HighSpeed →

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