All OpenAI models

GPT-5.3-Codex

OpenAI · released 5 months ago

GPT-5.3-Codex is a OpenAI model with a 400K token context window — about 570 pages of text. It reads Text, Images, and Files and replies in Text. It can show its reasoning before it answers.

$2.01

input / 1M tokens

$16.10

output / 1M tokens

400K

context — about 570 pages

2.3¢

a client proposal

Pricing

Input
$2.01 per million tokens
Output
$16.10 per million tokens
Cached input
$0.201 per million tokens
Web search
1.1¢ per search

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
OpenAI
Released
5 months ago (2026-02-24)
Context window
400K tokens — about 570 pages
Max output
128K tokens per reply
Input
Text, Images, and Files
Output
Text
Reasoning
Shows its thinking before answering

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$2.42$4.830 tokens250k500k750k1000k
GPT-5.3-Codex

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

GPT-5.3-Codex

OpenAI

1.2¢

for this task

33% input · 67% output

Full pricing →

Your $5 welcome credit covers about 414 of these.

Compare GPT-5.3-Codex

Closest in price on a typical task:

GPT-5.3-Codex vs GPT-5.2 →GPT-5.3-Codex vs GPT-5.2 Chat →GPT-5.3-Codex vs GPT-5.2-Codex →GPT-5.3-Codex vs GPT-5.3 Chat →Any other combination →

Questions, answered

How much does GPT-5.3-Codex cost on Alyph?

GPT-5.3-Codex costs $2.01 per million input tokens and $16.10 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 2.3¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is GPT-5.3-Codex's context window?

400K tokens — about 570 pages. Replies can be up to 128K tokens long.

Can GPT-5.3-Codex read images and files?

GPT-5.3-Codex reads Text, Images, and Files. Drop a file onto the canvas and it becomes part of the context — the only limit is the context window.

Does GPT-5.3-Codex show its reasoning?

Yes. GPT-5.3-Codex can expose its thinking before the final answer, so you can watch how it got there.

Test GPT-5.3-Codex against GPT-5.2

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.

Sign up free Try the demo