⌘K

Qwen Flash Character CN

qwen-flash-character-cn

Qwen Flash Character CN is a Qwen role-play chat model for character conversation scenarios. It supports OpenAI-compatible chat completions and is routed to the China-region Qwen character provider.

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID to use for the request

Value: qwen-flash-character-cn

messages array required

Array of message objects representing the role-play conversation history

role string required

Message role

Options: user, assistant, system, developer

content string | array required

Text string or multimodal message content. For role-play scenarios, use system or developer messages to define character settings, tone, and behavior

max_tokens integer

Maximum tokens to generate in the completion

Range: 1 - 4096

temperature number

Sampling temperature. Higher values make role-play responses more varied

Default: 1.0

Range: 0.0 - 2.0

top_p number

Nucleus sampling parameter

Default: 1.0

Range: 0.0 - 1.0

stream boolean

Whether to stream response incrementally

Default: false

character_options object

Role-play extension options. This object is passed at the same level as model and messages, and can define character profile, long-term memory, realtime awareness, or knowledge search settings

profile string

Character profile. Use it to replace or supplement persona instructions in system messages

enable_realtime boolean

Whether to enable realtime date and time awareness

Default: false

vector_store_ids array

Knowledge base ID list for enabling knowledge search

memory object

Long-term memory configuration. When long-term memory is enabled, also pass the session header x-dashscope-aca-session

Response Format

Returns an OpenAI-compatible chat completion object with generated assistant messages and token usage.