qwen3.5-plus

更新时间:
复制 MD 格式

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.

Inference Service Provider

The inference service provider for qwen3.5-plus is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

Capability Support Capability Support

Input Modality

Text Image Video

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 Image Video

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Germany (Frankfurt)

Scope: Global

Capability Support Capability Support

Input Modality

Text Image Video

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

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 Image Video

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

Parameter Value Parameter Value

Max Input Length

991808

Max Output Length

65536

Context Window

1000000

Max Input Length (Thinking Mode)

983616

Max Output Length (Thinking Mode)

65536

Max Chain-of-Thought Length

81920

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

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

Input(Batch File)

0.4

Per 1M tokens

Output(Batch File)

2.4

Per 1M tokens

Explicit Cache Creation

1

Per 1M tokens

Explicit Cache Read

0.08

Per 1M tokens

Input(Batch Chat)

0.8

Per 1M tokens

Output(Batch Chat)

4.8

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

Input(Batch File)

1

Per 1M tokens

Output(Batch File)

6

Per 1M tokens

Explicit Cache Creation

2.5

Per 1M tokens

Explicit Cache Read

0.2

Per 1M tokens

Input(Batch Chat)

2

Per 1M tokens

Output(Batch Chat)

12

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Input(Batch File)

2

Per 1M tokens

Output(Batch File)

12

Per 1M tokens

Explicit Cache Creation

5

Per 1M tokens

Explicit Cache Read

0.4

Per 1M tokens

Input(Batch Chat)

4

Per 1M tokens

Output(Batch Chat)

24

Per 1M tokens

Singapore

Scope: International

Input<=256k

Billing Item Price (CNY) Unit

Input

2.936

Per 1M tokens

Output

17.614

Per 1M tokens

Explicit Cache Creation

3.67

Per 1M tokens

Explicit Cache Read

0.294

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

3.67

Per 1M tokens

Output

22.018

Per 1M tokens

Explicit Cache Creation

4.587

Per 1M tokens

Explicit Cache Read

0.367

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

Explicit Cache Creation

1

Per 1M tokens

Explicit Cache Read

0.08

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

Explicit Cache Creation

2.5

Per 1M tokens

Explicit Cache Read

0.2

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Explicit Cache Creation

5

Per 1M tokens

Explicit Cache Read

0.4

Per 1M tokens

US (Virginia)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

Explicit Cache Creation

1

Per 1M tokens

Explicit Cache Read

0.08

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

Explicit Cache Creation

2.5

Per 1M tokens

Explicit Cache Read

0.2

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Explicit Cache Creation

5

Per 1M tokens

Explicit Cache Read

0.4

Per 1M tokens

Rate Limits

China (Beijing)

Parameter Value

RPM (Requests Per Minute)

30000

TPM (Tokens Per Minute)

5,000,000

Singapore

Scope: International

Parameter Value

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

5,000,000

Germany (Frankfurt)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

30000

TPM (Tokens Per Minute)

5,000,000

US (Virginia)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

30000

TPM (Tokens Per Minute)

5,000,000

Snapshot Versions

qwen3.5-plus-2026-04-20

The Qwen3.5 native vision-language series Plus model has seen a substantial improvement in agentic coding capabilities compared to the February 15th snapshot. Inference speed has also been significantly enhanced, while its knowledge retention, reasoning ability, and long-context processing remain at a high level, making it well-suited for complex agent-based tasks. It is ideal for applications such as coding agents, production workflows, and high-throughput scenarios. This version is based on a snapshot taken on April 20, 2026.

Inference Service Provider

The inference service provider for qwen3.5-plus-2026-04-20 is Alibaba Cloud Model Studio.

Model Capabilities

Capability Support Capability Support

Input Modality

Image Text Video

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

Parameter Value Parameter Value

Max Input Length

991808

Max Output Length

65536

Context Window

1000000

Max Input Length (Thinking Mode)

983616

Max Output Length (Thinking Mode)

65536

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

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

Explicit Cache Creation

1

Per 1M tokens

Explicit Cache Read

0.08

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

Explicit Cache Creation

2.5

Per 1M tokens

Explicit Cache Read

0.2

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Explicit Cache Creation

5

Per 1M tokens

Explicit Cache Read

0.4

Per 1M tokens

Singapore

Scope: International

Input<=256k

Billing Item Price (CNY) Unit

Input

2.936

Per 1M tokens

Output

17.614

Per 1M tokens

Explicit Cache Creation

3.67

Per 1M tokens

Explicit Cache Read

0.2936

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

3.67

Per 1M tokens

Output

22.018

Per 1M tokens

Explicit Cache Creation

4.5875

Per 1M tokens

Explicit Cache Read

0.367

Per 1M tokens

Rate Limits

China (Beijing)

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

Singapore

Scope: International

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

qwen3.5-plus-2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.This version is a snapshot as of February 15, 2026.

Inference Service Provider

The inference service provider for qwen3.5-plus-2026-02-15 is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

Capability Support Capability Support

Input Modality

Text Image Video

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 Image Video

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

Germany (Frankfurt)

Scope: Global

Capability Support Capability Support

Input Modality

Text Image Video

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

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 Image Video

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

Context Limits

Parameter Value Parameter Value

Max Input Length

991808

Max Output Length

65536

Context Window

1000000

Max Input Length (Thinking Mode)

983616

Max Output Length (Thinking Mode)

65536

Max Chain-of-Thought Length

81920

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

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Singapore

Scope: International

Input<=256k

Billing Item Price (CNY) Unit

Input

2.936

Per 1M tokens

Output

17.614

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

3.67

Per 1M tokens

Output

22.018

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

US (Virginia)

Scope: Global

Input<=128k

Billing Item Price (CNY) Unit

Input

0.8

Per 1M tokens

Output

4.8

Per 1M tokens

128k<Input<=256k

Billing Item Price (CNY) Unit

Input

2

Per 1M tokens

Output

12

Per 1M tokens

256k<Input<=1m

Billing Item Price (CNY) Unit

Input

4

Per 1M tokens

Output

24

Per 1M tokens

Rate Limits

China (Beijing)

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

Singapore

Scope: International

Parameter Value

RPM (Requests Per Minute)

60

TPM (Tokens Per Minute)

1,000,000

Germany (Frankfurt)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

US (Virginia)

Scope: Global

Parameter Value

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000