Document updated on Sep 30, 2026

Alibaba Cloud Qwen Integration

The Alibaba Cloud integration enables KrakenD to talk to the Qwen family of models through Alibaba Cloud Model Studio, allowing you to embed language model capabilities into your API workflows without custom coding. Use it when you want to connect Qwen for tasks like intelligent automation, conversational AI, content generation, or other LLM-driven functionalities inside your existing API infrastructure.

This component abstracts the complexities of communicating with Alibaba’s API. When an API request hits your KrakenD endpoint configured with the Alibaba interface, KrakenD automatically constructs the necessary payload, handles authentication, and processes the responses uniformly. This consistent integration also allows you to switch between different LLM vendors without changing client-facing interfaces.

In essence, the user sends the textual content or instructions, and KrakenD manages the complete interaction with Alibaba behind the scenes.

Configuration of the Alibaba Integration

To enable the Alibaba interface, add a backend in KrakenD with the alibaba vendor under the ai/llm namespace of its extra_config. For example:

{
  "endpoint": "/qwen",
  "method": "POST",
  "backend": [
    {
      "host": [
        "https://token-plan.ap-southeast-1.maas.aliyuncs.com"
      ],
      "url_pattern": "/compatible-mode/v1/responses",
      "method": "POST",
      "extra_config": {
        "ai/llm": {
          "alibaba": {
            "v1": {
              "credentials": "sk-xxxx",
              "debug": false,
              "variables": {
                "model": "qwen3.8-flash"
              }
            }
          }
        }
      }
    }
  ]
}

The host and url_pattern above point to Alibaba’s default endpoint. Change the host to reach the region where your Model Studio account lives. The credentials hold your Alibaba API key; set them through an environment variable instead of writing the key in the configuration.

To interact with the LLM, the user can send in the request:

• instructions (optional): If you want to add a system prompt
• contents: The content you want to send to the template

Like this:

$curl -XPOST --json '{"instructions": "Act as a 1000 dollar consultant", "contents": "Tell me a consultant joke"}' http://localhost:8080/qwen

The configuration options are:

This design keeps user input clean and focused only on content, while KrakenD handles building the full API request.

Declaring Alibaba in the Provider Inventory

Instead of repeating the configuration in every backend, you can declare Alibaba once in the LLM provider inventory and reference it by name from ai/llm or the AI Router. When you omit endpoint and model, the inventory uses Alibaba’s default endpoint and the qwen3.8-flash model:

{
  "$schema": "https://www.krakend.io/schema/krakend.json",
  "version": 4,
  "extra_config": {
    "ai/providers": {
      "providers": [
        {
          "name": "qwen",
          "provider": "alibaba",
          "credentials": "sk-xxxx"
        }
      ]
    }
  }
}

Customizing the Payload Sent and Received from Alibaba

As it happens with all LLM interfaces of KrakenD, you can completely replace the request and the response so you have a custom interaction with the LLM. While the default template should allow you to accomplish any day to day job, you might need to extend it using your own template.

You may override the input and output Go templates by specifying:

• input_template: Path to a custom template controlling how the request data is formatted before sending it to Alibaba.
• output_template: Path to a custom template to transform and extract the desired pieces from Alibaba’s response.

Use variables.extra_payload to pass additional attributes to your custom input_template, accessible as {{ .variables.extra_payload.yourchosenkey }}.

When you don’t declare an output_template, the response from the AI is returned inside the ai_gateway_response field. If you prefer another name, add a mapping attribute to the backend without changing the template:

{
  "url_pattern": "/compatible-mode/v1/responses",
  "mapping": {
    "ai_gateway_response": "my_response"
  }
}