Qwen Chat Format (Text Generation)¶

Official Documentation

📝 Introduction¶

Given a list of messages comprising a conversation, the model will return a response. Qwen is a large-scale language model independently developed by the Tongyi Lab under Alibaba Group, supporting multilingual conversations, text generation, code generation, and more.

🤖 Supported Models¶

Currently supported models include:

Model	Description
qwen-turbo	Qwen Turbo chat model
qwen-plus	Qwen Plus chat model
qwen-max	Qwen Max chat model

💡 Request Examples¶

Basic Text Chat ✅¶

curl --location "https://computevault.unodetech.xyz/api/v1/services/aigc/text-generation/generation" \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "qwen-plus",
    "input": {
      "messages": [
        {
          "role": "system",
          "content": "You are a helpful assistant."
        },
        {
          "role": "user",
          "content": "Who are you?"
        }
      ]
    },
    "parameters": {
      "result_format": "message"
    }
  }'

Response Example:

{
  "output": {
    "text": "",
    "finish_reason": "",
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": "Hello! I'm Qwen, a large-scale language model independently developed by the Tongyi Lab under Alibaba Group. I can answer questions, create text such as stories, official documents, emails, scripts, perform logical reasoning, coding, and more. I can also express opinions and play games. I support 100 languages, including but not limited to Chinese, English, German, French, Spanish, etc., meeting international usage needs. If you have any questions or need assistance, feel free to let me know anytime!",
          "role": "assistant"
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 23,
    "output_tokens": 106,
    "total_tokens": 129
  },
  "code": "",
  "message": "",
  "request_id": ""
}

📮 Request¶

Endpoint¶

POST /api/v1/services/aigc/text-generation/generation

Create a model response for a given chat conversation.

Authentication Method¶

Include the following in the request headers for API key authentication:

Authorization: Bearer $API_KEY

Where $API_KEY is your API key.

Request Body Parameters¶

`model`¶

Type: String
Required: Yes

The ID of the model to use. For example: qwen-plus, qwen-turbo, etc.

`input`¶

Type: Object
Required: Yes

An object containing input messages.

input Properties:

Property	Type	Required	Description
`messages`	Array	Yes	A list of messages comprising the conversation.

`input.messages`¶

Type: Array
Required: Yes

The list of messages comprising the conversation so far.

Message Types:

Message Type	Description
System message	System message used to set the assistant's behavior and role.
User message	Messages sent by the terminal user, containing prompts or additional context information.
Assistant message	Messages sent by the model in response to user messages.

System message Properties:

Property	Type	Required	Description
`role`	String	Yes	The role of the message author, here "system".
`content`	String	Yes	The content of the system message.

User message Properties:

Property	Type	Required	Description
`role`	String	Yes	The role of the message author, here "user".
`content`	String	Yes	The content of the user message.

Assistant message Properties:

Property	Type	Required	Description
`role`	String	Yes	The role of the message author, here "assistant".
`content`	String	No	The content of the assistant message.

`parameters`¶

Type: Object
Required: No

Configuration for generation parameters.

parameters Properties:

Property	Type	Required	Description
`result_format`	String	No	Response format. Optional values: `message`, `text`. Default is `message`.
`temperature`	Number	No	Sampling temperature, controlling the randomness of the output. Typically ranges from 0 to 2.
`top_p`	Number	No	Nucleus sampling parameter, controlling the probability mass for sampling.
`max_tokens`	Integer	No	Maximum number of tokens to generate.
`stop`	String or Array	No	Stop sequences, when the model generates these sequences, it stops generating.

📥 Response¶

Text Generation Object¶

Returns a text generation object.

`output`¶

Type: Object
Description: Output object containing the generated text and choices.

output Properties:

Property	Type	Description
`text`	String	The generated text content.
`finish_reason`	String	The reason for completion.
`choices`	Array	A list of generated choices.

`output.choices`¶

Type: Array
Description: A list of generated response options.

choice Properties:

Property	Type	Description
`finish_reason`	String	The reason the model stopped generating tokens. Possible values: `stop` (natural stop), `length` (reached maximum length), etc.
`message`	Object	The message generated by the model.
`message.role`	String	The role of the message author, usually "assistant".
`message.content`	String	The content of the message.

`usage`¶

Type: Object
Description: Usage statistics for the completion request.

usage Properties:

Property	Type	Description
`input_tokens`	Integer	The number of tokens in the input.
`output_tokens`	Integer	The number of tokens in the generated completion.
`total_tokens`	Integer	The total number of tokens used in the request (input + output).

`code`¶

Type: String
Description: Response code, usually an empty string indicating success.

`message`¶

Type: String
Description: Response message, usually an empty string indicating success.

`request_id`¶

Type: String
Description: The unique identifier for the request.

Text Generation Object Response Example¶

{
  "output": {
    "text": "",
    "finish_reason": "",
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": "Hello! I'm Qwen, a large-scale language model independently developed by the Tongyi Lab under Alibaba Group. I can answer questions, create text such as stories, official documents, emails, scripts, perform logical reasoning, coding, and more. I can also express opinions and play games. I support 100 languages, including but not limited to Chinese, English, German, French, Spanish, etc., meeting international usage needs. If you have any questions or need assistance, feel free to let me know anytime!",
          "role": "assistant"
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 23,
    "output_tokens": 106,
    "total_tokens": 129
  },
  "code": "",
  "message": "",
  "request_id": ""
}

Qwen Chat Format (Text Generation)¶

📝 Introduction¶

🤖 Supported Models¶

💡 Request Examples¶

Basic Text Chat ✅¶

📮 Request¶

Endpoint¶

Authentication Method¶

Request Body Parameters¶

model¶

input¶

input.messages¶

parameters¶