All Products
Search
Document Center

Alibaba Cloud Model Studio:deepseek-v4-pro

Last Updated:Sep 11, 2026

A flagship MoE large model with 1.6 trillion parameters and 49 billion activated parameters, natively supporting context lengths of up to one million tokens. Trained on a vast corpus of high-quality data, it excels in advanced mathematical reasoning, complex logical inference, specialized coding, and deep analysis of long-form text, making it well-suited for demanding applications such as cutting-edge research, sophisticated office workflows, and advanced AI agents.

Inference Service Provider

The inference service provider for deepseek-v4-pro is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

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

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Germany (Frankfurt)

Scope: Global

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

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

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Japan (Tokyo)

Scope: Global

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

1000000

Max Output Length

393216

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)

Billing ItemPrice (USD)Unit

Input

1.65

Per 1M tokens

Output

3.301

Per 1M tokens

Input(Implicit Cache)

0.138

Per 1M tokens

Singapore

Scope: International

Billing ItemPrice (USD)Unit

Input

2.4

Per 1M tokens

Output

4.8

Per 1M tokens

Input(Implicit Cache)

0.2

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Billing ItemPrice (USD)Unit

Input

1.65

Per 1M tokens

Output

3.301

Per 1M tokens

Input(Implicit Cache)

0.138

Per 1M tokens

US (Virginia)

Scope: Global

Billing ItemPrice (USD)Unit

Input

1.65

Per 1M tokens

Output

3.301

Per 1M tokens

Input(Implicit Cache)

0.138

Per 1M tokens

Japan (Tokyo)

Scope: Global

Billing ItemPrice (USD)Unit

Input

1.65

Per 1M tokens

Output

3.301

Per 1M tokens

Input(Implicit Cache)

0.138

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

Singapore

Scope: International

ParameterValue

RPM (Requests Per Minute)

10000

TPM (Tokens Per Minute)

1,200,000

Germany (Frankfurt)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

US (Virginia)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

Japan (Tokyo)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

10000

TPM (Tokens Per Minute)

1,200,000

Snapshot Versions

deepseek-v4-pro-0813

MoE , 1.6T, 49B, ., , , , , , .

Inference Service Provider

The inference service provider for deepseek-v4-pro-0813 is Alibaba Cloud Model Studio.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

1000000

Max Output Length

393216

Context Window

1000000

Max Input Length (Thinking Mode)

1000000

Max Output Length (Thinking Mode)

393216

Max Chain-of-Thought Length

393216

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 (USD)Unit

Input

0.636

Per 1M tokens

Input

1.272

Per 1M tokens

Output

1.908

Per 1M tokens

Output

3.816

Per 1M tokens

Input(Implicit Cache)

0.064

Per 1M tokens

Input(Implicit Cache)

0.127

Per 1M tokens

Singapore

Scope: International

Billing ItemPrice (USD)Unit

Input

0.66

Per 1M tokens

Input

1.32

Per 1M tokens

Output

1.98

Per 1M tokens

Output

3.96

Per 1M tokens

Input(Implicit Cache)

0.066

Per 1M tokens

Input(Implicit Cache)

0.132

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Billing ItemPrice (USD)Unit

Input

0.636

Per 1M tokens

Input

1.272

Per 1M tokens

Output

1.908

Per 1M tokens

Output

3.816

Per 1M tokens

Input(Implicit Cache)

0.064

Per 1M tokens

Input(Implicit Cache)

0.127

Per 1M tokens

US (Virginia)

Scope: Global

Billing ItemPrice (USD)Unit

Input

0.636

Per 1M tokens

Input

1.272

Per 1M tokens

Output

1.908

Per 1M tokens

Output

3.816

Per 1M tokens

Input(Implicit Cache)

0.064

Per 1M tokens

Input(Implicit Cache)

0.127

Per 1M tokens

Japan (Tokyo)

Scope: Global

Billing ItemPrice (USD)Unit

Input

0.636

Per 1M tokens

Input

1.272

Per 1M tokens

Output

1.908

Per 1M tokens

Output

3.816

Per 1M tokens

Input(Implicit Cache)

0.064

Per 1M tokens

Input(Implicit Cache)

0.127

Per 1M tokens

Hong Kong (China)

Scope: Global

Billing ItemPrice (USD)Unit

Input

0.636

Per 1M tokens

Input

1.272

Per 1M tokens

Output

1.908

Per 1M tokens

Output

3.816

Per 1M tokens

Input(Implicit Cache)

0.064

Per 1M tokens

Input(Implicit Cache)

0.127

Per 1M tokens

Rate Limits

China (Beijing)

This region uses dynamic rate limiting. The TPM limit is tiered by your monthly Model Studio spend, and the RPM limit is high enough that normal use does not trigger throttling. For the tier values, see Dynamic rate limiting.

Singapore

Scope: International

This region uses dynamic rate limiting. The TPM limit is tiered by your monthly Model Studio spend, and the RPM limit is high enough that normal use does not trigger throttling. For the tier values, see Dynamic rate limiting.

Germany (Frankfurt)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

US (Virginia)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

Japan (Tokyo)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000

Hong Kong (China)

Scope: Global

ParameterValue

RPM (Requests Per Minute)

15000

TPM (Tokens Per Minute)

1,200,000