OpenAI: GPT-5.3-Codex: AI model
GPT-5.3-Codex is an OpenAI model. An agentic coding model built for long, tool-using software-engineering runs, with up to 400K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 400,000 tokens
- Input:
- $1.75/1M tokens
- Output:
- $14/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: xhigh · high · medium · low · none
GPT-5.3-Codex is an agentic coding model built for long, tool-using software-engineering runs. GPT-5.3-Codex combines frontier software-engineering skill with broad reasoning: it is tuned for multi-language coding, terminal use and real-world computer-use, supports interactive steering mid-run, and is roughly 25% faster and more token-efficient than earlier Codex models. It supports a context window of up to 400K tokens.
GPT-5.3-Codex is served through Hormouz behind an OpenAI-compatible API. It supports tool calling, image (vision) input and step-by-step reasoning. Point your base URL at Hormouz and drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.
Pricing is usage-based: $1.75 per million input tokens and $14 per million output tokens. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
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...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.3-codex",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text, Image |
| Context window | 400,000 tokens |
| Pricing | $1.75/M in · $14.00/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Ranking distribution
11795 tournaments ?
Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.3-codex",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="openai/gpt-5.3-codex",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "openai/gpt-5.3-codex",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: GPT-5.3-Codex API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: GPT-5.3-Codex and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does GPT-5.3-Codex cost?
- Billing is usage-based: $1.75 per million input tokens and $14 per million output tokens. There is no fixed monthly fee. You pay only for what you use, and current rates are shown in the Hormouz dashboard.
- How do I access GPT-5.3-Codex from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to GPT-5.3-Codex from inside Iran, with no foreign credit card or circumvention tooling required.
- Is GPT-5.3-Codex compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and chat-completions code run without a rewrite.
- What context window and capabilities does GPT-5.3-Codex have?
- GPT-5.3-Codex supports a context window of up to 400K tokens. It also supports tool calling, image (vision) input and step-by-step reasoning. That makes it a good fit for agentic coding, debugging, long-running build-and-deploy workflows, and structured knowledge work such as document drafting and spreadsheet analysis.
- What is GPT-5.3-Codex good for?
- GPT-5.3-Codex works well for agentic coding, debugging, long-running build-and-deploy workflows, and structured knowledge work such as document drafting and spreadsheet analysis.
- Does GPT-5.3-Codex support streaming?
- Yes. Responses can be streamed token by token over the OpenAI-compatible API, which is ideal for chat UIs and low-latency apps. You call it the same way as any other chat model on Hormouz.
Updated 2026-10-13