> ## Documentation Index
> Fetch the complete documentation index at: https://masaic-ai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Codex With Your Own Model

> Run OpenAI Codex with OpenResponses using any model of your choice

# OpenAI Codex With Your Own Model

## Codex In Action With OpenResponses

<video width="100%" controls>
  <source src="https://mintcdn.com/masaic-ai/pMpPfUENOnyopgM0/assets/Codex-Demo-fast.mp4?fit=max&auto=format&n=pMpPfUENOnyopgM0&q=85&s=fbfbebb57ac5c90f8ab67a8fb07ea8e7" type="video/mp4" data-path="assets/Codex-Demo-fast.mp4" />

  Your browser does not support the video tag.
</video>

## Key Benefits

* **Run Codex with Custom Models**: Integrate [OpenAI Codex](https://github.com/openai/codex) with OpenResponses to use any model of your choice
* **Extend Functionality**: Enhance Codex capabilities with additional MCP tools or custom tools and integrations
* **Simple Deployment**: Quick setup with no separate installation needed - just follow the [quickstart guide](/quickstart)
* **Full Control**: Maintain complete ownership of your code data and model choices

## Step-by-Step Setup Instructions

### 1. Run OpenResponses Service

Launch OpenResponses using Docker:

```bash theme={null}
docker run -p 8080:8080 masaicai/open-responses:latest
```

For advanced configuration options, refer to the detailed [quickstart guide](/quickstart).

### 2. Install OpenAI Codex

Install the Codex CLI globally:

```bash theme={null}
npm i -g @openai/codex
```

For more information about Codex CLI, visit the [official repository](https://github.com/openai/codex).

### 3. Configure and Run Codex with Your Preferred Model

Set OpenResponses as your base API and configure your API key:

```bash theme={null}
# Point to your OpenResponses instance
export OPENAI_BASE_URL=http://localhost:6644/v1

# Configure your API key (use the key from your model provider, e.g., OpenAI, Claude, etc.)
export OPENAI_API_KEY=your-api-key-here
```

Run Codex with a specific model using the `-m` flag:

### Example with Locally Deployed Model

```bash theme={null}
codex -m "http://mymodel_host/v1@my_model" "explain me the structure of the codebase"
```

### Example with Claude

```bash theme={null}
codex -m "claude@claude-3-5-haiku-20241022" "explain me the structure of the codebase"
```

### Example with DeepSeek

```bash theme={null}
codex -m "deepseek@deepseek-chat" "analyze this repository"
```

### Example with Google Gemini

```bash theme={null}
codex -m "google@gemini-2.0-flash" "help me understand this code"
```

The format for specifying a model is `provider@model-name` or `model_endpoint@model_name`, where:

* `provider`: The model provider (e.g., claude, deepseek, google, openai)
* `model_endpoint`: For locally deployed models or any custom model provider, the endpoint URL where chat/completions is available
* `model-name`: The specific model to use from that provider or endpoint

## Supported Model Providers

OpenResponses supports a variety of model providers that can be used with the `provider@model_name` convention. For a complete list of supported providers with detailed examples for each, see our [Model Providers](/model-providers) documentation.