Configure Model Providers

It is recommended to use CC Switch to complete the configuration — an open-source provider management tool with a visual interface, so there is no need to manually edit JSON or environment variables.

1. Install CC Switch

macOS

Or go to Releases to download the .dmg file for manual installation.

Windows

Go to Releases to download the .msi installer.

Linux

2. Add the api.tokenhotAI Provider

Step 1: Add a New Provider

Open CC Switch, go to the provider management page, and click the + button in the top-right corner.

Step 2: Fill in the Configuration

Fill in the fields as shown below, then click + Add to complete.

Config Item	Value	Description
❶ Provider Name	`my Codex`	Custom
❷ Official Website		Provider official website
❸ API Key	Your Tokenhot API Key	Get it from api.tokenhot.ai
❹ Request URL		Do not add a trailing slash
❺ API Format	`OpenAI Compatible`	OpenAI-compatible format
❽ Write to General Configuration	✅ Checked	Write to the global configuration so it takes effect for all projects

Step 3: Enable the Provider

After adding it, go back to the list, select My codex, and click the Use button. When you see the "Switched successfully" message, the setup is complete. Make sure Write to General Configuration is checked, and the configuration will be automatically written to config.toml.

3. Verify the Configuration

If an AI response is returned normally, the configuration is successful.

4. Specify a Model

For recommended models, please refer to the Tokenhot Model Marketplace.

Troubleshooting

Q: It says "Authentication error"

Make sure the API Key has been entered correctly, and check that the request URL does not end with a slash.

Q: Connection timeout

Make sure the request URL is https://api.tokenhot.ai and does not end with a slash.

Configure Model Providers

1. Install CC Switch#

macOS#

Windows#

Linux#

2. Add the api.tokenhotAI Provider#

Step 1: Add a New Provider#

Step 2: Fill in the Configuration#

Step 3: Enable the Provider#

3. Verify the Configuration#

4. Specify a Model#

Troubleshooting#