Alibaba Cloud (Qwen) integration guide
VerifiedHow to connect Alibaba Cloud (Qwen) to WEXTL and use its 21 actions in your workflows. About Alibaba Cloud (Qwen): The Alibaba Cloud Model Studio platform for Qwen language, vision and media models.
- 4 searches
- 17 actions
- Polling
- Auth: API key
AI-assisted documentation10 min read
This documentation is compiled from our integration source code, internal specs for Alibaba Cloud (Qwen), its official API documentation and anonymized requests logs we collect from our support team[2].
Requirements
Get your Alibaba Cloud (Qwen) credentials
- API KeypasswordRequired
A Model Studio API key created in the same region and workspace as the Workspace ID below. Keys from one region do not work in another.[1]
- Workspace IDtextRequired
Copy it from Workspace Details in the Model Studio console. It is the first part of your workspace address, for example ws-abc123 in ws-abc123.ap-southeast-1.maas.aliyuncs.com.[1]
- RegionselectRequired
The region your workspace was created in. If Alibaba Cloud adds a region that is not listed, its region code is still accepted.[1]
- Probe ModeltextRequired
A chat model enabled in this workspace. Saving the connection sends it one very short message to check the key and workspace, which uses a few tokens.[1]
Connect Alibaba Cloud (Qwen) in WEXTL
- Log in to your WEXTL account, add the Alibaba Cloud (Qwen) node module to your workflow, and click Create new credential.
- Optional: In the Credential name field, enter a name for the credential.
- Enter the authentication credentials you copied from your Alibaba Cloud (Qwen) account, or follow the on-screen instructions to create the credential.
- If prompted, authenticate your account and confirm access.
- If you want to make changes to your credential in the future, follow the steps in Manage credentials →
Alibaba Cloud (Qwen) triggers and actions on WEXTL
The list below is a reference of every Alibaba Cloud (Qwen) node module the integration supports. You will be able to pick any of them on the workflow canvas while building automations.
Each Alibaba Cloud (Qwen) node module below opens to reveal its input parameters, outputs, and connection requirements.
Get a Response
SearchOne stored answer with its state.
| Field | Type |
|---|---|
Response IDRequired | text |
| Field | Type |
|---|---|
| Response ID | text |
| Object | text |
| Status | text |
| Created At (Unix Seconds) | number |
| Completed At (Unix Seconds) | number |
| Model | text |
| Stored | boolean |
| Temperature | number |
| Top P | number |
| Parallel Tool Calls | boolean |
| Tool Choice | text |
| Service Tier | text |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Total Tokens | number |
| Input Tokens Details | object |
| Output Tokens Details | object |
| Output Items | array |
Get an Async Task Result
SearchStatus and result of a queued generation task.
| Field | Type |
|---|---|
Task IDRequired | text |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Task ID | text |
| Task Status (PENDING, RUNNING, SUCCEEDED, FAILED, CANCELED or UNKNOWN) | text |
| Submit Time (UTC+8) | text |
| Scheduled Time (UTC+8) | text |
| End Time (UTC+8) | text |
| Results (Image and Multi-File Tasks) | array |
| Result (Single-File Transcription) | object |
| Video URL (valid 24 hours) | url |
| Original Prompt | text |
| Rewritten Prompt | text |
| Usage | object |
| Image Count | number |
| Video Count | number |
| Duration (Seconds) | number |
| Output Video Duration (Seconds) | number |
| Aspect Ratio | text |
| Resolution Tier | number |
| Audio Seconds | number |
List Models
SearchCatalog models with filters for kind, maker and feature.
| Field | Type |
|---|---|
LimitRequired | number |
| Capability | choice |
| Name Contains | text |
| Exact Model ID | text |
| Provider | choice |
| Feature | choice |
| Deployment Mode | choice |
| Response Language | choice |
| Field | Type |
|---|---|
| Model ID | text |
| Name | text |
| Description | text |
| Provider | text |
| Inference Provider | text |
| Published Time | text |
| Equivalent Snapshot | text |
| Model Info | object |
| Context Window | number |
| Max Input Tokens | number |
| Max Output Tokens | number |
| Max Reasoning Tokens | number |
| Reasoning Max Input Tokens | number |
| Reasoning Max Output Tokens | number |
| Inference Metadata | object |
| Input Modalities | array |
| Output Modalities | array |
| Capabilities | array |
| Capability | text |
| Features | array |
| Feature | text |
| Prices | array |
List Response Input Items
SearchInputs behind a stored model response.
| Field | Type |
|---|---|
Response IDRequired | text |
LimitRequired | number |
| Order | choice |
| Field | Type |
|---|---|
| Item ID | text |
| Type | text |
| Role | text |
| Status | text |
| Content | array |
Create a Chat Completion
ActionModel reply to a conversation via the compatible chat endpoint.
| Field | Type |
|---|---|
ModelRequired | choice |
MessagesRequired | array |
| Message | object |
| Max Tokens | number |
| Temperature | number |
| Top P | number |
| Presence Penalty | number |
| Seed | number |
| Stop Sequences | array |
| Stop Sequence | text |
| Response Format | choice |
| Enable Thinking | boolean |
| Field | Type |
|---|---|
| ID | text |
| Object | text |
| Created (Unix Seconds) | number |
| Model | text |
| System Fingerprint | text |
| Usage | object |
| Prompt Tokens | number |
| Completion Tokens | number |
| Total Tokens | number |
| Prompt Tokens Details | object |
| Choices | array |
Create a Message
ActionQwen reply in the Anthropic message format.
| Field | Type |
|---|---|
ModelRequired | text |
MessagesRequired | array |
| Message | object |
Max TokensRequired | number |
| System Prompt | text |
| Temperature | number |
| Top P | number |
| Stop Sequences | array |
| Stop Sequence | text |
| Field | Type |
|---|---|
| Message ID | text |
| Type | text |
| Role | text |
| Model | text |
| Content Blocks | array |
| Stop Reason | text |
| Stop Sequence | text |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Cache Creation Input Tokens | number |
| Cache Read Input Tokens | number |
Create a Model Response
ActionResponses-API call that can build on a stored response.
| Field | Type |
|---|---|
ModelRequired | choice |
InputRequired | text |
| Instructions | text |
| Previous Response ID | text |
| Max Output Tokens | number |
| Temperature | number |
| Top P | number |
| Store Response | boolean |
| Field | Type |
|---|---|
| Response ID | text |
| Object | text |
| Created At (Unix Seconds) | number |
| Status | text |
| Model | text |
| Parallel Tool Calls | boolean |
| Tool Choice | text |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Total Tokens | number |
| Input Tokens Details | object |
| Output Tokens Details | object |
| Output Items | array |
Create a Multimodal Embedding
ActionVectors for mixed text, image and video content.
| Field | Type |
|---|---|
ModelRequired | choice |
ContentsRequired | array |
| Item | object |
| Dimension | number |
| Video Frame Rate | number |
| Instruction | text |
| Fuse Into One Embedding | boolean |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Embeddings | array |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Total Tokens | number |
| Image Tokens | number |
| Input Tokens Details | object |
Create a Multimodal Generation
ActionAnswers about pictures and video clips from a model.
| Field | Type |
|---|---|
ModelRequired | choice |
MessagesRequired | array |
| Message | object |
| Max Tokens | number |
| Temperature | number |
| Top P | number |
| Enable Thinking | boolean |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Choices | array |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Image Tokens | number |
| Video Tokens | number |
| Input Tokens Details | object |
Create a Rerank
ActionRelevance ranking from the compatible service.
| Field | Type |
|---|---|
ModelRequired | text |
QueryRequired | text |
DocumentsRequired | array |
| Document | text |
| Top N | number |
| Ranking Instruction | text |
| Field | Type |
|---|---|
| Request ID | text |
| Object | text |
| Model | text |
| Usage | object |
| Total Tokens | number |
| Results | array |
Create a Speech Synthesis
ActionSpoken audio from text with a chosen system voice.
| Field | Type |
|---|---|
ModelRequired | choice |
TextRequired | text |
VoiceRequired | text |
| Language | choice |
| Instructions | text |
| Optimize Instructions | boolean |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Finish Reason | text |
| Audio | object |
| Usage | object |
| Characters | number |
| Input Tokens | number |
| Output Tokens | number |
| Total Tokens | number |
Create a Text Embedding
ActionVectors from the native embedding service.
| Field | Type |
|---|---|
ModelRequired | choice |
TextsRequired | array |
| Text | text |
| Text Type | choice |
| Dimension | number |
| Output Type | choice |
| Instruction | text |
| Field | Type |
|---|---|
| Request ID | text |
| Usage | object |
| Total Tokens | number |
| Output | object |
| Embeddings | array |
Create a Text Generation
ActionNative text model reply to a conversation.
| Field | Type |
|---|---|
ModelRequired | choice |
MessagesRequired | array |
| Message | object |
| Max Tokens | number |
| Temperature | number |
| Top P | number |
| Seed | number |
| Enable Thinking | boolean |
| Field | Type |
|---|---|
| Request ID | text |
| Usage | object |
| Input Tokens | number |
| Output Tokens | number |
| Total Tokens | number |
| Output | object |
| Text | text |
| Finish Reason | text |
| Choices | array |
Create a Text Rerank
ActionRanked documents from the native rerank service.
| Field | Type |
|---|---|
ModelRequired | text |
QueryRequired | text |
DocumentsRequired | array |
| Document | text |
| Top N | number |
| Return Document Text | boolean |
| Ranking Instruction | text |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Results | array |
| Usage | object |
| Total Tokens | number |
Create a Transcription Job
ActionQueues audio transcription and returns the task details.
| Field | Type |
|---|---|
ModelRequired | choice |
| File URLs | array |
| URL | text |
| File URL | url |
| Language Hints | array |
| Language Code | text |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Task ID | text |
| Task Status | text |
Create a Video Generation Task
ActionQueues a video render and returns its task details.
| Field | Type |
|---|---|
ModelRequired | choice |
PromptRequired | text |
| Negative Prompt | text |
| Audio URL | url |
| Resolution | choice |
| Aspect Ratio | choice |
| Size | text |
| Duration (Seconds) | number |
| Rewrite Prompt | boolean |
| Add Watermark | boolean |
| Seed | number |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Task ID | text |
| Task Status | text |
Create an Image
ActionSynchronous image generation or editing from a text prompt.
| Field | Type |
|---|---|
ModelRequired | choice |
PromptRequired | text |
| Input Images | array |
| Image URL | text |
| Number of Images | number |
| Size | text |
| Negative Prompt | text |
| Seed | number |
| Rewrite Prompt | boolean |
| Add Watermark | boolean |
| Field | Type |
|---|---|
| Created (Unix Seconds) | number |
| Images | array |
| Usage | object |
| Output Width | number |
| Output Height | number |
| Input Image Count | number |
| Input Image Type | text |
| Output Image Count | number |
| Output Image Type | text |
Create an Image Generation Task
ActionQueues an image job and returns its task details.
| Field | Type |
|---|---|
ModelRequired | choice |
PromptRequired | text |
| Negative Prompt | text |
| Size | text |
| Rewrite Prompt | boolean |
| Add Watermark | boolean |
| Seed | number |
| Field | Type |
|---|---|
| Request ID | text |
| Output | object |
| Task ID | text |
| Task Status | text |
Create Embeddings
ActionText vectors from the OpenAI-compatible embeddings endpoint.
| Field | Type |
|---|---|
ModelRequired | choice |
InputRequired | text |
| Dimensions | number |
| Field | Type |
|---|---|
| ID | text |
| Object | text |
| Model | text |
| Data | array |
| Usage | object |
| Prompt Tokens | number |
| Total Tokens | number |
Templates
Look for Alibaba Cloud (Qwen) templates in the WEXTL template library.
Browse templates →Other AI integrations on WEXTL
Cody AI[2]AI assistants that answer questions from your own documents.
AirtopRun cloud browser sessions and extract or interact with web pages using Airtop.
AgentXHosted AI agents for starting conversations, sending messages and reading traces.
DeepSeekOpen-weight large language models for reasoning, coding, and conversation.
ApiframeSingle API wrapping Midjourney, Flux, and other image, video, and music models.
References
- WEXTL® Alibaba Cloud (Qwen) Source Code connector implementation.
- Our users use cases and automations.
- Official API Documentation for Alibaba Cloud (Qwen).
- WEXTL® visual workflow builder data.
Last updated: Nov 13, 2026 09:46
How we write our apps documentation
How we compile these docs: sources, the role of AI, and how we verify.





























