DocsICP FilingConsole
官方文档
首页

qwen-flash

更新时间：
复制 MD 格式
产品详情
我的收藏

The Qwen3 Flash model offers a powerful fusion of thinking and non-thinking modes with dynamic in-conversation switching, excelling in complex reasoning while showing significant gains in instruction following and text comprehension. It supports a 1M context length and is billed on a tiered model corresponding to context usage.This model version is functionally equivalent to the snapshot model qwen-flash-2025-07-28.

Inference Service Provider

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

Model Capabilities

China (Beijing)

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Supported

Fine-tuning

Unsupported

Singapore

Scope: International

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Germany (Frankfurt)

Scope: Global

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

US (Virginia)

Scope: Global

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

Parameter Value Parameter Value

Max Input Length

997952

Max Output Length

32768

Context Window

1000000

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)

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.03

Per 1M tokens

Input(Batch File)

0.075

Per 1M tokens

Output(Batch File)

0.75

Per 1M tokens

Explicit Cache Creation

0.188

Per 1M tokens

Explicit Cache Read

0.015

Per 1M tokens

Input(Batch Chat)

0.15

Per 1M tokens

Output(Batch Chat)

1.5

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

Input(Implicit Cache)

0.12

Per 1M tokens

Input(Batch File)

0.3

Per 1M tokens

Output(Batch File)

3

Per 1M tokens

Explicit Cache Creation

0.75

Per 1M tokens

Explicit Cache Read

0.06

Per 1M tokens

Input(Batch Chat)

0.6

Per 1M tokens

Output(Batch Chat)

6

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

Input(Implicit Cache)

0.24

Per 1M tokens

Input(Batch File)

0.6

Per 1M tokens

Output(Batch File)

6

Per 1M tokens

Explicit Cache Creation

1.5

Per 1M tokens

Explicit Cache Read

0.12

Per 1M tokens

Input(Batch Chat)

1.2

Per 1M tokens

Output(Batch Chat)

12

Per 1M tokens

Singapore

Scope: International

Input<=256k

Billing Item Price (CNY) Unit

Input

0.367

Per 1M tokens

Output

2.936

Per 1M tokens

Input(Implicit Cache)

0.073

Per 1M tokens

Input(Batch File)

0.183

Per 1M tokens

Output(Batch File)

1.468

Per 1M tokens

Explicit Cache Creation

0.462

Per 1M tokens

Explicit Cache Read

0.037

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.835

Per 1M tokens

Output

14.678

Per 1M tokens

Input(Implicit Cache)

0.367

Per 1M tokens

Input(Batch File)

0.917

Per 1M tokens

Output(Batch File)

7.339

Per 1M tokens

Explicit Cache Creation

2.297

Per 1M tokens

Explicit Cache Read

0.183

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.03

Per 1M tokens

Explicit Cache Creation

0.188

Per 1M tokens

Explicit Cache Read

0.015

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

Input(Implicit Cache)

0.12

Per 1M tokens

Explicit Cache Creation

0.75

Per 1M tokens

Explicit Cache Read

0.06

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

Input(Implicit Cache)

0.24

Per 1M tokens

Explicit Cache Creation

1.5

Per 1M tokens

Explicit Cache Read

0.12

Per 1M tokens

US (Virginia)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

Input(Implicit Cache)

0.03

Per 1M tokens

Explicit Cache Creation

0.188

Per 1M tokens

Explicit Cache Read

0.015

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

Input(Implicit Cache)

0.12

Per 1M tokens

Explicit Cache Creation

0.75

Per 1M tokens

Explicit Cache Read

0.06

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

Input(Implicit Cache)

0.24

Per 1M tokens

Explicit Cache Creation

1.5

Per 1M tokens

Explicit Cache Read

0.12

Per 1M tokens

Rate Limits

China (Beijing)

Parameter Value

RPM (Requests Per Minute)

30000

TPM (Tokens Per Minute)

10,000,000

Singapore

Scope: International

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

5,000,000

Germany (Frankfurt)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

30000

TPM (Tokens Per Minute)

10,000,000

US (Virginia)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

5,000,000

Snapshot Versions

qwen-flash-2025-07-28

The Qwen3 Flash model (snapshot 2025-07-28) offers a powerful fusion of thinking and non-thinking modes with dynamic in-conversation switching, excelling in complex reasoning while showing significant gains in instruction following and text comprehension. It supports a 1M context length and is billed on a tiered model corresponding to context usage.

Inference Service Provider

The inference service provider for qwen-flash-2025-07-28 is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Unsupported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Singapore

Scope: International

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Unsupported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Germany (Frankfurt)

Scope: Global

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Unsupported

Batch Inference

Unsupported

Fine-tuning

Unsupported

US (Virginia)

Scope: Global

Capability Support Capability Support

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Unsupported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

Parameter Value Parameter Value

Max Input Length

997952

Max Output Length

32768

Context Window

1000000

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)

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

Singapore

Scope: International

Input<=256k

Billing Item Price (CNY) Unit

Input

0.367

Per 1M tokens

Output

2.936

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.835

Per 1M tokens

Output

14.678

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

US (Virginia)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.15

Per 1M tokens

Output

1.5

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

0.6

Per 1M tokens

Output

6

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

1.2

Per 1M tokens

Output

12

Per 1M tokens

Rate Limits

China (Beijing)

Parameter Value

RPM (Requests Per Minute)

60

TPM (Tokens Per Minute)

1,000,000

Singapore

Scope: International

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

5,000,000

Germany (Frankfurt)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

60

TPM (Tokens Per Minute)

1,000,000

US (Virginia)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

5,000,000
Previous：qwen3.5-flashNext：qwen-flash-us