How much does GPT-5.3 Codex cost?

GPT-5.3 Codex costs $1.75 per million input tokens and $14 per million output tokens on standard pricing; other tiers (Standard, Fast (Priority)) are also available. A workload of 20M input and 5M output tokens a month is about $105.

What is the context length of GPT-5.3 Codex?

GPT-5.3 Codex accepts up to 400,000 tokens (400K) of input and can return up to 128,000 tokens in one response.

Does GPT-5.3 Codex support tool calling and structured outputs?

Yes, GPT-5.3 Codex supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Deterministic seed, Prompt caching.

What inputs and outputs does GPT-5.3 Codex support?

GPT-5.3 Codex accepts Text, Image, PDF as input and produces Text as output.

Which providers serve GPT-5.3 Codex?

GPT-5.3 Codex is available from 3 API providers: Azure, OpenAI, OpenAI. Prices can differ by provider.

When was GPT-5.3 Codex released?

GPT-5.3 Codex was released by OpenAI in 2026.

GPT-5.3 Codex

gpt-5.3-codex

API Provider site

GPT-5.3 tuned for agentic software engineering; powers Codex. Fast mode costs $3.50 / $28 per 1M. Built by OpenAI.

Prices updated recently

Input price

$1.75

per 1M tokens · Standard

Output price

$14

per 1M tokens · Standard

Input limit

400K

tokens

Output limit

128K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

GPT-5.3 Codex price history

2 price records since 9/25/2026

GPT-5.3 Codex cost calculator

Input20M tokens

Output5M tokens

$105/month

Standard pricing

Overview

What is GPT-5.3 Codex?

GPT-5.3 Codex is a code & slms and text & reasoning model from OpenAI. GPT-5.3 tuned for agentic software engineering; powers Codex. Fast mode costs $3.50 / $28 per 1M. Its 400K context window and $1.75 input price make it a candidate for quality-focused production applications.

Code generationAgent workflowsContent workflowsClassification

Benchmarks

GPT-5.3 Codex benchmarks & speed

How GPT-5.3 Codex scores on standardized evaluations, and where it lands among every model we track.

32.5

Intelligence Index

Better than 76% of 153 models

102tok/s

Output speed

Better than 58% of 119 models

1148

DesignArena Elo

Better than 28% of 81 models

Reasoning

GPQA Diamond

91.5%

Graduate-level scientific reasoning · top 16%

HLE

42.5%

Humanity's Last Exam · top 15%

Latency & design

Time to first token: 68.72s
DesignArena win rate: 47.2%
Design battles judged: 15,675

Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.

Rates

GPT-5.3 Codex pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$1.75

Per 1M tokens

Cached input · Standard

$0.17

Per 1M tokens

Capabilities

GPT-5.3 Codex Tools

Tools available when using GPT-5.3 Codex through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Supported

Built-in web search

Not supported

Log probabilities

Not supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Supported

Where to run it

GPT-5.3 Codex API providers

3 providers serve GPT-5.3 Codex. Prices are per 1M tokens; uptime is the last 24 hours.

Provider	Input	Output	Cached	Context	Uptime
Azure	$1.75	$14	$0.17	400K	99.9%
OpenAI	$1.75	$14	$0.17	400K	100%
OpenAI	$3.50	$28	$0.35	400K	—

Azure

Input: $1.75
Output: $14
Cached: $0.17
Context: 400K
Uptime: 99.9%

OpenAI

Input: $1.75
Output: $14
Cached: $0.17
Context: 400K
Uptime: 100%

OpenAI

Input: $3.50
Output: $28
Cached: $0.35
Context: 400K
Uptime: —

Strengths and limitations

Strengths

Measured results (AA Intelligence 32.5 · DesignArena Elo 1148 · Arena Elo 1244 · MMLU-Pro 81%) position it for demanding production work.
400K context supports large documents, repositories and extended conversations.
Supports code & slms and text & reasoning workloads in one model.

Limitations

Generated tokens cost 8× more than input tokens, which matters for verbose responses.
Large context capacity does not guarantee consistent retrieval across the entire prompt.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider

More models from OpenAI

View provider →

GPT-3.5 Turbo

OpenAI

16K

$0.50 in · $1.50 out

View model

GPT-3.5 Turbo (older v0613)

OpenAI

$1.00 in · $2.00 out

View model

GPT-3.5 Turbo 16k

OpenAI

16K

$3.00 in · $4.00 out

View model

GPT-3.5 Turbo Instruct

OpenAI

$1.50 in · $2.00 out

View model

Frequently asked questions about GPT-5.3 Codex

GPT-5.3 Codex is a code & slms and text & reasoning model from OpenAI. GPT-5.3 tuned for agentic software engineering; powers Codex. Fast mode costs $3.50 / $28 per 1M.