Configure Model Providers

We recommend using CC Switch to complete the configuration — an open-source provider management tool with visual controls, no need to manually edit JSON or environment variables.

1. Install CC Switch

macOS

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

Windows

Go to Releases to download the .msi installer.

Linux

2. Add 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 Configuration

Fill in as shown below and click + Add to complete.

Configuration Item	Value	Description
❶ Provider Name	`api.tokenhot.ai-claude`	Custom
❷ Website URL		Provider website
❸ API Key	Your api.tokenhotAI API Key	Obtain at api.tokenhot.ai
❹ Request URL		Do not add a trailing slash
❺ API Format / Auth Field	`Anthropic Messages (Native)` / `ANTHROPIC_AUTH_TOKEN (Default)`	Keep default
❻ Model Configuration	Leave empty	Leave empty to use default Claude models
❼ Options	Check "Hide AI Attribution" and "Teammates Mode"	Check as needed
❽ Write to Global Config	✅ Checked	Write to global configuration, effective for all projects

Step 3: Enable the Provider

After adding, return to the list, select api.tokenhot.ai-claude, and click the Use button. A "Switch Successful" notification confirms it's done.

3. Verify Configuration

Navigate to your project directory and start Claude Code:

Press Esc on first launch to skip login. After starting, check the top info bar — confirming that API Usage Billing (❶) is displayed means you are billed through api.tokenhot.ai:

If the above information is confirmed, the configuration is successful.

4. Using Other Models

Through api.tokenhotAI, you can use non-Claude models in Claude Code (such as Qwen, GLM, DeepSeek, etc.). Simply filter for compatible models in the model plaza, then configure the model mapping.

Step 1: Filter Compatible Models

Go to the tokenhot Model Plaza, and under API Protocol on the left, select Anthropic to filter for models that support the Anthropic protocol.

Step 2: Copy Model Name

Click the target model card — there is a copy button next to the model name to copy the model ID with one click (e.g., claude-opus-4.7).

Step 3: Configure Model Mapping

Return to CC Switch and find the Model Mapping section in the provider configuration. Fill the copied model name into the corresponding model slot. Visit the tokenhot Model Plaza to browse available models:

Mapping Slot	Description
Primary Model	Default model used by Claude Code
Thinking Model	Model used for deep reasoning
Haiku Default Model	Lightweight task model
Sonnet Default Model	Medium-complexity task model
Opus Default Model	High-complexity task model

Troubleshooting

When encountering issues, run /status in the Claude Code terminal to check the configuration:

/status

Confirm the following key fields:

❶ Anthropic base URL is https://api.api.tokenhot.ai/anthropic

❷ Model shows the currently used model

Q: "Authentication error"

Confirm that Anthropic base URL is correct and check whether the API Key is valid.

Q: Connection timeout

Confirm the request URL is https://api.api.tokenhot.ai without a trailing slash.

Q: Streaming response lag

api.tokenhotAI has built-in global acceleration — this is usually a local network issue. Check your local connection and retry.

Configure Model Providers

1. Install CC Switch#

macOS#

Windows#

Linux#

2. Add api.tokenhotAI Provider#

Step 1: Add a New Provider#

Step 2: Fill in Configuration#

Step 3: Enable the Provider#

3. Verify Configuration#

4. Using Other Models#

Step 1: Filter Compatible Models#

Step 2: Copy Model Name#

Step 3: Configure Model Mapping#

Troubleshooting#