CoPaw is an open-source Chinese AI agent developed by Alibaba Cloud's Tongyi Lab. CoPaw supports integrating any third-party model service compatible with the OpenAI protocol through its "Custom Provider" feature. By using the following configuration, you can integrate Tencent Cloud Token Plan models into CoPaw.
This article introduces how to configure and use Tencent Cloud Large Language Model Token Plan in CoPaw.
Prerequisites
Before starting the configuration, make sure you have completed the following preparatory work:
Operation Steps
Step 1: Start CoPaw and go to the model configuration page
After starting the CoPaw application, access http://127.0.0.1:8088 (the default port) in your browser, click Settings > Model in the left sidebar to go to the model configuration page.
Step 2: Add a custom provider
On the model configuration page, click Add Provider > Settings, fill in the following information, and then click Create.
|
Provider ID | tencent-token-plan
|
Display Name | Tencent Cloud Token Plan |
After successful creation, you will be able to see the newly added provider card on the page.
Step 3: Configure the provider
Click Settings on the newly added provider card and fill in the following connection parameters:
|
Base URL | https://tokenhub-intl.tencentcloudmaas.com/plan/v3
|
API Key | The dedicated API Key obtained after the Token Plan is purchased |
Save the settings after filling in.
Step 4: Add a model
Click Model on the custom provider card, enter the model ID in the Model ID input box, and then click Add Model. The following models are supported:
|
Auto | auto
|
GLM-5.2 | glm-5.2
|
Kimi-K2.6 | kimi-k2.6
|
MiniMax-M3 | minimax-m3
|
DeepSeek-V4-Flash (Vendor Direct) | deepseek-v4-flash-202605
|
DeepSeek-V4-Pro (Vendor Direct) | deepseek-v4-pro-202606
|
Add the required models one by one.
Step 5: Select and use a model
In the LLM Configuration section at the top of the page, select the newly added custom provider as the provider, choose the corresponding model, and click Save to start a conversation.