API Request Test

Open Linux Shell or Windows CMD terminal and paste the following command to run your first API request. Make sure to replace $YOUR_API_KEY with your API key.

curl Request Example

curl https://ai-tokenhub.com/api/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer $YOUR_API_KEY' \
  -d '{
  "model": "qwen3.5-plus",
  "messages": [{"role": "user", "content": "Say this is a test!"}],
  "temperature": 0.7
}'

Response Example

This request asks the model to complete the prompt "Say this is a test!" using the qwen3.5-plus model. You should receive a response similar to the following:

{
   "id":"chatcmpl-abc123",
   "object":"chat.completion",
   "created":1677858242,
   "model":"qwen3.5-plus",
   "usage":{
      "prompt_tokens":13,
      "completion_tokens":7,
      "total_tokens":20
   },
   "choices":[
      {
         "message":{
            "role":"assistant",
            "content":"\n\nThis is a test!"
         },
         "finish_reason":"stop",
         "index":0
      }
   ]
}

Response Field Description

Field	Description
id	Unique identifier for the request
object	Return object type, here is chat.completion
created	Unix timestamp of request creation time
model	Actual model name processed
usage	Token usage statistics
choices	List of model-generated responses
finish_reason	Generation completion reason, stop means normal completion

Now you have completed your first chat request. finish_reason being stop means the API returned the complete output generated by the model.