Roar AI
DiscordGet started
All models
OpenAI · Chat

GPT-5.3-Codex

GPT-5.3-Codex costs $1.75 per million input tokens and $14 per million output tokens on Roar AI. OpenAI’s coding specialist from early 2026, made for agents that work in a terminal.

Input$1.75per 1M tokens
Output$14per 1M tokens
Context window400Ktokens

GPT-5.3-Codex API pricing

Input$1.75 per 1M tokens
Output$14 per 1M tokens
Cached input$0.175 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $19.25. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byOpenAI
ReleasedFebruary 2026
TypeChat
Context window400K tokens
Longest answer128K tokens
ReadsText, images
Thinks before answeringAlways on
WeightsClosed
Processed inGlobal
Model idgpt-5.3-codex

About GPT-5.3-Codex

GPT-5.3-Codex was OpenAI’s dedicated model for Codex, its coding agent. It combined the coding of the earlier Codex model with the reasoning of GPT-5.2, and at launch scored 77.3% on Terminal-Bench 2.0 and 56.8% on SWE-Bench Pro. OpenAI says engineers used early versions of it to help debug its own training.

It always reasons, from low to extra-high effort. The general GPT-6 models have since caught up and passed it on coding, so it makes most sense where a workflow was built around it.

What is GPT-5.3-Codex good for?

  • Coding agents that work in a terminal.
  • Large refactors that touch many files.
  • Workflows already built around Codex.

GPT-5.3-Codex limitations

  • A generation behind GPT-6 on agentic coding.
  • Its knowledge stops at August 2025, and its 400K context is smaller than current flagships’.

How to use the GPT-5.3-Codex API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="gpt-5.3-codex",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

GPT-5.3-Codex FAQ

How much does GPT-5.3-Codex cost?

Input is $1.75 per 1M tokens; output is $14 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $19.25.

Can I use GPT-5.3-Codex alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from GPT-5.3-Codex to another model only means changing the model name in your code.

Is GPT-5.3-Codex open source?

No. OpenAI does not publish the weights, so it is only available through an API like this one.

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

GPT-5.3-Codex can read up to 400K tokens in one request, and write an answer of up to 128K tokens.

Can GPT-5.3-Codex read images and PDFs?

It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.

Start using GPT-5.3-Codex

Create a free account, get an API key and call GPT-5.3-Codex with the OpenAI SDK.