Token Plan Team Edition supports extending AI coding tool capabilities through built-in model tools, such as web search, code interpreter, and web scraping.
Tool overview
The Responses API of qwen3.7-max, qwen3.7-plus, qwen3.6-plus, and qwen3.6-flash models has five built-in tools: web search, code interpreter, web scraping, reverse image search, and text-to-image search. Once enabled, the model automatically invokes the corresponding tool when needed.
Pricing
Built-in model tools
The costs of built-in tools for qwen3.7-max, qwen3.7-plus, qwen3.6-plus, and qwen3.6-flash models can be deducted through Token Plan Team Edition. No additional charges apply for built-in tools; the token consumption is deducted from your plan Credits. For specific pricing, refer to the console model details page.
Usage
Use built-in tools of qwen3.7-max / qwen3.7-plus / qwen3.6-plus / qwen3.6-flash
Set the model in your AI tool to qwen3.7-max, qwen3.7-plus, qwen3.6-plus, or qwen3.6-flash, and ask questions directly in the conversation. The model will automatically invoke the corresponding built-in tool based on the question:
|
Tool |
Description |
|
Web search |
Retrieves information from the internet and generates answers based on search results. |
|
Code interpreter |
Enables a built-in Python code interpreter during model calls, allowing the model to write and run Python code in a sandbox environment to solve complex problems such as mathematical calculations and data analysis. |
|
Web scraping |
The web scraping tool can access a specified URL and extract its content to provide the model with the information it needs. |
|
Reverse image search |
Enables the model to search for visually similar images on the internet based on an input image, and analyze and reason based on the search results. Suitable for scenarios such as finding similar products and visual content tracing. |
|
Text-to-image search |
Enables the model to search for relevant images on the internet based on text descriptions, and describe and reason based on the image content. Suitable for scenarios such as visual Q&A and image recommendation. |