deepseek/deepseek-v4-pro

Online Chat

DeepSeek

通用长文本函数调用翻译代码数学RAG

Publish time

2026/4/24

Model Series

DeepSeek

Input type

Output type

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write Price

¥11.25 / 1M tokens

Cache Read Price

¥0.9 / 1M tokens

Context Window

1,000,000

Max Output Length

384,000

DeepSeek-V4 拥有百万字超长上下文，在 Agent 能力、世界知识和推理性能上均实现国内与开源领域的领先。相比前代模型，DeepSeek-V4-Pro 的 Agent 能力显著增强。在 Agentic Coding 评测中，V4-Pro 已达到当前开源模型最佳水平，并在其他 Agent 相关评测中同样表现优异。

Providers for deepseek/deepseek-v4-pro

Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.

Sort by

deepseek

国内

TTFT

0.04s

Throughput

37.28tps

Uptime

100.00%

Provider Model

deepseek/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

huaweicloud

国内

TTFT

No data

Throughput

4.25tps

Uptime

100.00%

Provider Model

huaweicloud/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月9日 2 AMNo data

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price

¥12 / 1M tokens

Output Price

¥24 / 1M tokens

Cache Write

¥15 / 1M tokens

Cache Read

¥1.2 / 1M tokens

paratera并行科技

国内

TTFT

No data

Throughput

29.63tps

Uptime

26.00%

Provider Model

paratera/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月9日 5 PM26.42%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-48%

¥6.24 / 1M tokens

Output Price-48%

¥12.48 / 1M tokens

Cache Write-48%

¥7.8 / 1M tokens

Cache Read-48%

¥0.052 / 1M tokens

国内

TTFT

2.08s

Throughput

78tps

Uptime

100.00%

Provider Model

st/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月10日 6 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-20%

¥9.6 / 1M tokens

Output Price-20%

¥19.2 / 1M tokens

Cache Write-20%

¥12 / 1M tokens

Cache Read-20%

¥0.08 / 1M tokens

tokenmall-cdtx

国内

TTFT

14.45s

Throughput

35.30tps

Uptime

100.00%

Provider Model

tokenmall-cdtx/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM99.90%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-40%

¥5.4 / 1M tokens

Output Price-40%

¥16.2 / 1M tokens

Cache Write-40%

¥6.75 / 1M tokens

Cache Read-40%

¥0.18 / 1M tokens

tokenmall-zqf

国内

TTFT

0.03s

Throughput

44.17tps

Uptime

100.00%

Provider Model

tokenmall-zqf/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM99.86%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsOpenAI ResponsesAnthropic Messages

Total Context

1,000,000

Max Output

384,000

Input Price-50%

¥4.5 / 1M tokens

Output Price-50%

¥13.5 / 1M tokens

Cache Write-50%

¥5.625 / 1M tokens

Cache Read-50%

¥0.15 / 1M tokens

火

火山引擎

国内

TTFT

1.24s

Throughput

45.27tps

Uptime

100.00%

Provider Model

volcengine/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price-50%

¥4.5 / 1M tokens

Output Price-50%

¥13.5 / 1M tokens

Cache Write-50%

¥5.625 / 1M tokens

Cache Read-50%

¥0.45 / 1M tokens

腾

腾讯混元

国内

TTFT

0.73s

Throughput

54.87tps

Uptime

99.00%

Provider Model

tencent/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM98.81%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

通

通义千问

国内

TTFT

0.07s

Throughput

54.67tps

Uptime

100.00%

Provider Model

alibaba/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

Performance for deepseek/deepseek-v4-pro

Compare different providers across Zhinao API

Throughput

49.61 tok/s

TTFT

No data

Uptime for deepseek/deepseek-v4-pro

Uptime for deepseek/deepseek-v4-pro across all providers

Sample code and API for deepseek/deepseek-v4-pro

Get API Key

Zhinao API normalizes requests and responses across providers for you

View full docs

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.360.cn/v1",
  apiKey: process.env.ZHINAO_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro",
  messages: [
    { role: "user", content: "Hello, how are you?" }
  ],
  temperature: 0.7,
  max_tokens: 1000,
});

console.log(response.choices[0].message.content);

deepseek/deepseek-v4-pro

Online Chat

DeepSeek

通用长文本函数调用翻译代码数学RAG

Publish time

2026/4/24

Model Series

DeepSeek

Input type

Output type

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write Price

¥11.25 / 1M tokens

Cache Read Price

¥0.9 / 1M tokens

Context Window

1,000,000

Max Output Length

384,000

Providers for deepseek/deepseek-v4-pro

Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.

Sort by

deepseek

国内

TTFT

0.04s

Throughput

37.28tps

Uptime

100.00%

Provider Model

deepseek/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

huaweicloud

国内

TTFT

No data

Throughput

4.25tps

Uptime

100.00%

Provider Model

huaweicloud/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月9日 2 AMNo data

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price

¥12 / 1M tokens

Output Price

¥24 / 1M tokens

Cache Write

¥15 / 1M tokens

Cache Read

¥1.2 / 1M tokens

paratera并行科技

国内

TTFT

No data

Throughput

29.63tps

Uptime

26.00%

Provider Model

paratera/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月9日 5 PM26.42%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-48%

¥6.24 / 1M tokens

Output Price-48%

¥12.48 / 1M tokens

Cache Write-48%

¥7.8 / 1M tokens

Cache Read-48%

¥0.052 / 1M tokens

国内

TTFT

2.08s

Throughput

78tps

Uptime

100.00%

Provider Model

st/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月10日 6 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-20%

¥9.6 / 1M tokens

Output Price-20%

¥19.2 / 1M tokens

Cache Write-20%

¥12 / 1M tokens

Cache Read-20%

¥0.08 / 1M tokens

tokenmall-cdtx

国内

TTFT

14.45s

Throughput

35.30tps

Uptime

100.00%

Provider Model

tokenmall-cdtx/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM99.90%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat Completions

Total Context

1,000,000

Max Output

384,000

Input Price-40%

¥5.4 / 1M tokens

Output Price-40%

¥16.2 / 1M tokens

Cache Write-40%

¥6.75 / 1M tokens

Cache Read-40%

¥0.18 / 1M tokens

tokenmall-zqf

国内

TTFT

0.03s

Throughput

44.17tps

Uptime

100.00%

Provider Model

tokenmall-zqf/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM99.86%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsOpenAI ResponsesAnthropic Messages

Total Context

1,000,000

Max Output

384,000

Input Price-50%

¥4.5 / 1M tokens

Output Price-50%

¥13.5 / 1M tokens

Cache Write-50%

¥5.625 / 1M tokens

Cache Read-50%

¥0.15 / 1M tokens

火

火山引擎

国内

TTFT

1.24s

Throughput

45.27tps

Uptime

100.00%

Provider Model

volcengine/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price-50%

¥4.5 / 1M tokens

Output Price-50%

¥13.5 / 1M tokens

Cache Write-50%

¥5.625 / 1M tokens

Cache Read-50%

¥0.45 / 1M tokens

腾

腾讯混元

国内

TTFT

0.73s

Throughput

54.87tps

Uptime

99.00%

Provider Model

tencent/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM98.81%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

通

通义千问

国内

TTFT

0.07s

Throughput

54.67tps

Uptime

100.00%

Provider Model

alibaba/deepseek/deepseek-v4-pro

Supported Parameters

temperaturetop_ptop_k

Recent Uptime

10月11日 11 PM100.00%

Reasoning

Toggleable

Supported Response Formats

OpenAI Chat CompletionsAnthropic MessagesOpenAI Responses

Total Context

1,000,000

Max Output

384,000

Input Price

¥9 / 1M tokens

Output Price

¥27 / 1M tokens

Cache Write

¥11.25 / 1M tokens

Cache Read

¥0.9 / 1M tokens

Performance for deepseek/deepseek-v4-pro

Compare different providers across Zhinao API

Throughput

49.61 tok/s

TTFT

No data

Uptime for deepseek/deepseek-v4-pro

Uptime for deepseek/deepseek-v4-pro across all providers

Sample code and API for deepseek/deepseek-v4-pro

Get API Key

Zhinao API normalizes requests and responses across providers for you

View full docs

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.360.cn/v1",
  apiKey: process.env.ZHINAO_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro",
  messages: [
    { role: "user", content: "Hello, how are you?" }
  ],
  temperature: 0.7,
  max_tokens: 1000,
});

console.log(response.choices[0].message.content);