Tokener CA
Service online
Sign up
DocsCline Integration

Cline Integration

Integrate Tokener CA in Cline through an OpenAI Compatible provider.

Updated:

Applicable Scenarios

Cline is an AI coding assistant for VS Code. It supports an OpenAI Compatible provider, so you can directly configure Tokener CA as a custom model provider for code understanding, editing, command execution confirmation, and project-level Agent tasks.

For the integration you need to prepare:

Configuration ItemValue
API ProviderOpenAI Compatible
Base URLhttps://a.skypool.xyz/v1
API KeyConsumer API Key, for example stc-...
Model IDPlatform model name, for example gemma4:26b

Configure in Cline Settings

Open the Cline panel in VS Code, go to the settings page, and fill it in as follows:

FieldWhat to Fill In
API ProviderSelect OpenAI Compatible
Base URLhttps://a.skypool.xyz/v1
API KeyConsumer API Key
Modelgemma4:26b, or the platform model ID you want to use

Note: Cline's Base URL should be filled in up to /v1; do not fill in the full /v1/chat/completions. Cline will automatically append the chat interface path according to the OpenAI-compatible protocol.

Model Capability Configuration

Cline allows you to supplement the context length, maximum output, image capability, and tool capability for a custom model. We recommend configuring conservative values first, then adjusting according to the model page instructions:

Capability ItemRecommendation
Context WindowFill in according to the model page's context length; when unsure, first fill in 32768 or 128000
Max Output TokensFirst fill in 4096 or 8192
Image SupportOnly enable when the target model supports image input
Computer Use / Tool UseEnable when you need Cline to perform tool or code-editing tasks
Input / Output PriceCan be filled in according to the platform model page prices, used for local cost estimation

Verify the Connection

After saving the configuration, send a small task in the Cline conversation:

Text
Please read the currently open file and explain what it does in three sentences.

If Cline can return a result and the corresponding request appears in the Tokener CA Token console's activity records, the integration is successful.

You can also first get curl working with the same Key and model:

Bash
curl -X POST "https://a.skypool.xyz/v1/chat/completions" \  -H "Authorization: Bearer <consumer_api_key>" \  -H "Content-Type: application/json" \  --data-raw '{    "model": "gemma4:26b",    "messages": [      {        "role": "user",        "content": "Please return a short message confirming the integration succeeded."      }    ],    "max_tokens": 64,    "stream": false  }'

Troubleshooting Checklist

SymptomHow to Handle
Authentication failureCheck whether the API Key was copied completely and whether it is filled in the OpenAI Compatible API Key field
Model does not existCheck whether the Model ID exactly matches the platform model list
404Check whether the Base URL is https://a.skypool.xyz/v1, without adding /chat/completions
Output is very shortIncrease Max Output Tokens
Tool calls unstableConfirm the model is suitable for tool calling and enable the corresponding capability in the Cline model configuration

References