Deepseek V4 Pro

DeepSeek
deepseek/deepseek-v4-pro

V4 Pro, 1M context

Context Window

1.0M

1,048,576 tokens

Max Output

384K

384,000 tokens

About this model

DeepSeek V4 Pro is the latest flagship DeepSeek model available through Alibaba Cloud Bailian, built for complex reasoning, long-context code understanding, and agentic engineering tasks. It supports a 1M token context window and benefits from Bailian context-cache pricing.

Use it for deeper planning, complex codebase changes, and long-document analysis through Chuizi.AI with a single ck- API key.

Highlights

1M context
V4 flagship
Bailian cache pricing
Strong reasoning

Best For

Complex codebase workLong-context reasoningAgent planningTechnical review
2026-04-24MoEMoE TransformerProprietary

Capabilities

ChatReasoningCodecache

Pricing (per 1M tokens)

Pricing (per 1M tokens)/ 1M tokens
Input / 1M$1.75
Output / 1M$3.50
Cache Read$0.350
Cache Write$2.19

Final prices shown

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

FAQ

Related Models