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.

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $22.14 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.

GPT-5.3-Codex is billed in rupees, on the same monthly invoice as every other model your team uses — no foreign card, no separate OpenAI account, and one key for all of it.

Prompts sent to GPT-5.3-Codex are processed outside Sri Lanka. If a workload has to stay in the country, Qwen3.8-27B (Colombo) runs on our own servers in Colombo.

Use the OpenAI SDK you already have — point it at Roar AI and name the model. 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."}],
)