qwen-flash-character

Updated at:

A Qwen-series multilingual role-playing model. This is a dynamically updated version, and model updates are announced in advance. It is suited to anthropomorphic role-playing, with optimizations for constrained persona instruction-following, topic progression, and empathetic listening, and supports deep restoration of personalized characters.

Inference Service Provider

The inference service provider for qwen-flash-character is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Singapore

Scope: International

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

US (Virginia)

Scope: Global

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

China (Beijing)

ParameterValueParameterValue

Max Input Length

8,192

Max Output Length

4,096

Context Window

8,192

Singapore

Scope: International

ParameterValueParameterValue

Max Input Length

32,768

Max Output Length

32,768

Context Window

32,768

US (Virginia)

Scope: Global

ParameterValueParameterValue

Max Input Length

8,192

Max Output Length

4,096

Context Window

8,192

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.

China (Beijing)

Billing ItemPrice (CNY)Unit

Input

0.25

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.05

Per 1M tokens

Singapore

Scope: International

Billing ItemPrice (CNY)Unit

Input

0.375

Per 1M tokens

Output

2.998

Per 1M tokens

Input(Implicit Cache)

0.075

Per 1M tokens

US (Virginia)

Scope: Global

Billing ItemPrice (CNY)Unit

Input

0.25

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.05

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

120

TPM (Tokens Per Minute)

500,000

Singapore

Scope: International

ParameterValue

RPM (Requests Per Minute)

120

TPM (Tokens Per Minute)

500,000

US (Virginia)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

120

TPM (Tokens Per Minute)

500,000

Snapshot Versions

qwen-flash-character-2026-02-26

A multi-language role-playing model from the Qwen series, suitable for anthropomorphic role-playing, with optimized capabilities such as instruction following for constrained personas, topic progression, and empathetic listening, supporting deep restoration of personalized characters. This version is the snapshot as of February 26, 2026.

Inference Service Provider

The inference service provider for qwen-flash-character-2026-02-26 is Alibaba Cloud Model Studio.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

262,144

Max Output Length

32,768

Context Window

262,144

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.

China (Beijing)

Billing ItemPrice (CNY)Unit

Input

0.18

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.036

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

120

TPM (Tokens Per Minute)

500,000