GPT-5.3-Codex

OPENAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1506Chatbot Arena Verified

Max Context Limit400,000Max Out: 128,000 tokens

Prompt Caching90% OFF$0.17 / 1M cached

Standard API / 1M$15.75🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Coding & Logic
Fictional
Reasoning
Agentic
📋 Strict JSON Schema
🛠️ Native Tool Calling
🧠 Extended Test-Time Reasoning

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...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$1.75 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.17 / 1M

Output Tokens (Completion)$14.00 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupGPT-5.3-Codex vs Google: Gemini 3.8 Flash (batch)VS Engine MatchupGPT-5.3-Codex vs OpenAI: GPT-5.6 Terra Pro (batch)VS Engine MatchupGPT-5.3-Codex vs Google: Nano Banana 2 (Gemini 3.1 Flash Image)VS Engine MatchupGPT-5.3-Codex vs OpenAI: GPT-5.2-Codex VS Engine MatchupGPT-5.3-Codex vs OpenAI: GPT-5.1-Codex-Max VS Engine MatchupGPT-5.3-Codex vs OpenAI: GPT Astra Latest