DeepSeek-V4-Pro

deepseek-v4-pro

Open sourceDeepSeek series

Overview

1M ContextMathCode generationDocument analysis

DeepSeek-V4-Pro is a flagship MoE model for business-critical paths: 16T total parameters, 498B activated per inference, with native million-token context. It is optimized for hard reasoning and high-quality training data, with particular strength in mathematical logic, complex reasoning, professional code generation and long-document analysis — suited to high-throughput workloads and multi-step automation pipelines as a core engine on the critical path.

Native million-token context

Native million-token context loads large codebases, very long documents and multi-turn task history in one pass.

Flagship MoE scale

16T total / 498B activated, covering the hardest mathematics, code and logical reasoning tasks.

Complex task automation

Built for long-running agentic workflows and task orchestration across multi-step, long-chain automation.

Throughput and stability

RPM 15K / TPM 1.20M sustains steady output for high-concurrency online workloads.

Features

Prefix completion✓

Context caching✓

Structured output✓

Batch✓

Web search✓

Vision✕

Fine-tuning✕

Pricing

Off-peak prices are half of peak prices. Peak hours are Monday to Friday 9:00–12:00 and 14:00–18:00 Beijing time (UTC+8); all other times are off-peak.

Off-peak

Input¥4.5/M tokens

Input (cache hit)¥0.15/M tokens

Output¥13.5/M tokens

Peak

Input¥9/M tokens

Input (cache hit)¥0.3/M tokens

Output¥27/M tokens

Rate Limits & Context

Context Window1M

Max Output384K

RPM (requests/min)15K

TPM (tokens/min)1200K

API Reference

ENDPOINT

POST https://api.tokenfab.cn/v1/chat/completions

Request Example

curl https://api.tokenfab.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKENFAB_API_KEY" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "用一句话介绍旗舰版 DeepSeek-V4-Pro。"}
    ]
  }'

import os
from deepscope import Generation
import dashscope

dashscope.base_http_api_url = 'https://dashscope.aliyuncs.com/api/v1'

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': '用一句话介绍旗舰版 DeepSeek-V4-Pro。'}
]
response = Generation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='deepseek-v4-pro',
    messages=messages,
    result_format='message',
    enable_thinking=True,
)

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "用一句话介绍旗舰版 DeepSeek-V4-Pro。" }
  ]
});

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

Response Example

JSON

{
  "id": "chatcmpl-7h2k93fa",
  "object": "chat.completion",
  "created": 1784950000,
  "model": "deepseek-v4-pro",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "我是 DeepSeek-V4-Pro，旗舰版 MoE 大模型，总参 16T、激活 498B，原生支持百万级上下文，覆盖最难的数学、代码与长文本任务。"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 52,
    "total_tokens": 70
  }
}

Request Parameters

Parameter	Type	Required	Description
model	string	✓	Model ID, e.g. deepseek-v4-pro
messages	array	✓	List of chat messages, each with role and content
temperature	float	—	Sampling temperature, 0–2, default 0.7
top_p	float	—	Nucleus sampling, 0–1, default 0.9
max_tokens	int	—	Maximum output tokens
stream	bool	—	Whether to stream the response, default false
tools	array	—	Tool definitions for function calling
tool_choice	string	—	Tool choice policy: auto / none / a named function