AI Tools

CloudBase AI is compatible with the OpenAI API protocol, so any AI tool that supports a custom OpenAI-compatible endpoint (such as CodeBuddy, Cursor, Claude Code, Cline, etc.) can be connected to CloudBase large models.

Prerequisites

1. A CloudBase environment with its Environment ID (ENV_ID)
2. A Token Resource Pack purchased
3. Enable the required models in Console → AI → Text Models
4. A CloudBase API Key (Console → Environment Settings → API Key)

Configuration

Fill in the following settings in your AI tool:

Field	Value
Base URL	https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase/v1
API Key	Your CloudBase environment API Key
Model	deepseek-v4-flash (must be enabled in console; other enabled models also supported)

Replace <ENV_ID> with your actual CloudBase environment ID.

About the Provider

The cloudbase segment in the Base URL is CloudBase's unified provider, applicable to all models purchased via Token Resource Pack (DeepSeek, Hunyuan, Kimi, GLM, etc.). See the full model list.

Tool-specific Configuration

CodeBuddy

1. Open CodeBuddy Settings → Model Configuration
2. Select "Add Custom Model", set Provider to OpenAI Compatible
3. Fill in Base URL and API Key
4. Set the model name to deepseek-v4-flash

Cursor

1. Open Cursor Settings → Models
2. Enter your CloudBase API Key in the OpenAI API Key field
3. Enter the Base URL in Override OpenAI Base URL
4. Type deepseek-v4-flash in the model list and enable it

Cline / Roo Code

1. Open plugin settings → API Provider, select OpenAI Compatible
2. Fill in Base URL and API Key
3. Set Model ID to deepseek-v4-flash

Claude Code

claude config set api-url https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase/v1
claude config set api-key <YOUR_API_KEY>

Other OpenAI-compatible Tools

In your tool's model settings, replace the OpenAI endpoint with the Base URL above and provide your CloudBase API Key.