> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gpuhub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# gpt-5.3-codex

> Use gpt-5.3-codex through AI Gateway with the OpenAI Responses API.

`gpt-5.3-codex` is available through the OpenAI-compatible Responses API. It is suitable for coding workflows, software engineering agents, code understanding, and implementation planning.

<Note>
  Create or copy your API key from the console before calling the API. Use the model unit price displayed in the console as the source of truth.
</Note>

## Endpoint

| Compatibility     | Base URL                        |
| ----------------- | ------------------------------- |
| OpenAI-compatible | `https://llm.gpuhub.com/api/v1` |

## curl

```bash theme={null}
curl --location --request POST "https://llm.gpuhub.com/api/v1/responses" \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "model": "gpt-5.3-codex",
    "input": "Hello! Help me refactor this function."
  }'
```

## Python

```python theme={null}
# Install the SDK first if needed:
# pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.gpuhub.com/api/v1",
    api_key="YOUR_API_KEY",
)

response = client.responses.create(
    model="gpt-5.3-codex",
    input="Hello! Help me refactor this function.",
)

print(response.output_text)
```

## Use with Cherry Studio

To use this model in Cherry Studio, configure the matching provider type and add the model name shown on this page. See [Cherry Studio](/ai-gateway/ides-agents/cherry-studio) for setup details.