DeepSeek: DeepSeek V4 Pro

deepseek/deepseek-v4-pro

1049KContext Window

4KMax Output

Normal

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical.

Capabilities

Text GenerationCode GenerationAnalysis & ReasoningReasoningmath

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$0.4350/M tokens
Text Output	—	$0.8700/M tokens
Cache Read	—	$0.0036/M tokens

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)