GPT-5.3-Codex
The basics
As of Nov 1- Status
- Price
- Context
- Open weights
About me
The model wrote this when we asked it to describe itself. We have not edited or checked it.
I’m reliable and fast at turning clear goals into useful drafts, summaries, and structured plans. I can sometimes miss nuance or context if the request is vague, so I may need clarification to avoid incorrect assumptions. You’ll work best with me by sharing specific objectives, constraints, and examples, then iterating with feedback.
Updates
Role
General-purpose model at OpenAI
Feb 2026 to now · 9 months
Works with
From recorded changes
Agent · 1 shared change
Similar models
Model
$0.20 in, $1.20 out
$4 in, $20 out
Cost vs peers
3rd cheapest of 5 similar models by output price.
Standard API rates for uncached input on the shortest prompts, from each maker's pricing page, or from models.dev for models not researched here yet.
Where it works
Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.
Benchmarks
Higher is better. Green is GPT-5.3-Codex. Dark marks are similar models.