Try Out and Call Models - User¶
After deploying a model or choosing a platform preset model, you can use the model in two ways: chat online in the Playground, or create an API Key and call the model through the OpenAI-compatible API.
Prerequisites¶
- You have signed in to the console with a user that has the LLM Studio permission.
- A usable model is available: a platform preset public model, or a deployed model service.
Try It Online¶
-
In the left navigation, click Playground and select the model type (text models or image models).
You can also go to the Model Gallery and click Try Out on the target model card to enter the playground.
-
Select a model in the playground: public models can be tried out directly; deployed model services can be picked from the Model Services list.
-
Enter a question in the dialog box to chat with the model and experience its capabilities firsthand.

Create an API Key¶
-
In the left navigation, click API Keys, then click Create in the upper right corner.
-
Enter the API Key name (e.g.
test-key) and click OK to generate a new API Key.Note
The API Key is only fully displayed when it is first created. Save it immediately. If it leaks, delete it and generate a new one promptly.
Call Models via API¶
Use the OpenAI-compatible API. Take Python as an example:
import openai
openai.api_key = "your-api-key" # Replace with your API Key
openai.api_base = "https://sh-02.d.run" # Replace with the region of your model service
response = openai.Completion.create(
model="u-1100a15812cc/qwen2", # Replace with the access name of your model service
prompt="What is your name?"
)
print(response.choices[0].text)
Verification¶
Online chat returns responses normally, or an API call returns text generated by the model, which means the model is available.
Next Step¶
Connect the model to an intelligent Q&A app — see Build an Intelligent App. To learn about invocation methods and client integration, see Model Invocation.