OpenAI: GPT-5.3-Codex

OpenAI: GPT-5.3-Codex

openai · Released Feb 24, 2026 Professional
Intelligence #6 / 565
83.5 Our Score
Speed #153 / 262
84.8 tokens / sec
Input #468 / 566
$1.75 per 1M tokens
Output #511 / 566
$14.00 per 1M tokens
Context #81 / 566
400,000 tokens

Analysis Summary

OpenAI: GPT-5.3-Codex sits in the Professional tier on our leaderboard, ranked #6 of 565 published models on overall intelligence. At $1.75 input and $14.00 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, vision, and reasoning.

Editorial notes

GPT-5.3-Codex from OpenAI delivers frontier coding and reasoning with strong agentic performance, vision support, a 400K context window, and reliable tool use for complex business automation.

Assessed May 31, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence7.9Technical8.6Value6.5Content9
Intelligence 7.9/10
Technical 8.6/10
Content 9/10
Value 6.5/10

How OpenAI: GPT-5.3-Codex compares

OpenAI: GPT-5.3-Codex ranks #11 of 371 AI models we track for overall intelligence, #7 of 308 for coding, #13 of 283 for agentic tasks. Its 400K-token context window is larger than 86% of the models we list. At $1.75 per million input tokens it is cheaper than 17% of comparable models.

About OpenAI: GPT-5.3-Codex

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results..

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

53.6 Intelligence Index
53.1 Coding Index
69.5 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 91.5% Graduate-level scientific reasoning
HLE 39.9% Humanity's Last Exam
SciCode 53.2% Scientific computing

Technical

TerminalBench Hard 53% Agentic terminal tasks
τ²-Bench 86% Conversational agent benchmark

Content

IFBench 75.4% Instruction following
LCR 74% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does OpenAI: GPT-5.3-Codex stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID openai/gpt-5.3-codex
Provideropenai
Release Date February 24, 2026
Context Length400,000 tokens
Max Completion128,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.75 $0.001750
Output $14.00 $0.014000

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

99.5%
Avg Uptime
3,520ms
Best Latency (TTFT)
45 tok/s
Best Throughput
2/2
Active Endpoints
Available via: OpenAI, Azure

Frequently asked questions about OpenAI: GPT-5.3-Codex

How much does OpenAI: GPT-5.3-Codex cost?

OpenAI: GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens.

What is the context window of OpenAI: GPT-5.3-Codex?

OpenAI: GPT-5.3-Codex has a context window of 400,000 tokens (400K).

Is OpenAI: GPT-5.3-Codex good for coding?

On our coding benchmark index, OpenAI: GPT-5.3-Codex ranks #7 of 308 models, placing it in the top quartile of the field for code generation and debugging.

What can OpenAI: GPT-5.3-Codex do?

OpenAI: GPT-5.3-Codex supports image/vision input, tool use, and function calling.

Who created OpenAI: GPT-5.3-Codex?

OpenAI: GPT-5.3-Codex is developed by OpenAI and was released on February 24, 2026.