🚀 DeepSeek V4 API Guide

Why DeepSeek?

DeepSeek has emerged as one of China's most capable AI companies. Their models consistently rival GPT-4 on coding and reasoning benchmarks, at a fraction of the cost.

Available DeepSeek Models

Model	Context	Best For	Speed
deepseek-v4	128K	Latest flagship, general tasks	Medium
deepseek-v3	128K	Previous gen, proven reliability	Medium
deepseek-r1	128K	Chain-of-thought reasoning	Slower (thinking)
deepseek-v4-flash	64K	Fast, cost-efficient tasks	Fast

Quick Start — Python

from openai import OpenAI

# Connect to our unified API gateway
client = OpenAI(
    base_url="https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1",
    api_key="your-api-key"
)

# Use DeepSeek V4 just like OpenAI
response = client.chat.completions.create(
    model="deepseek-v4",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function to find prime numbers"}
    ],
    temperature=0.7,
    max_tokens=1024
)

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

Quick Start — JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1',
  apiKey: 'your-api-key'
});

const response = await client.chat.completions.create({
  model: 'deepseek-v4',
  messages: [
    { role: 'user', content: 'Explain recursion in simple terms' }
  ]
});

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

Quick Start — cURL

curl https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4",
    "messages": [
      {"role": "user", "content": "Hello, DeepSeek!"}
    ]
  }'

DeepSeek R1 — Reasoning Mode

DeepSeek R1 uses chain-of-thought reasoning for complex problems. Enable extended thinking for math, logic, and multi-step analysis:

response = client.chat.completions.create(
    model="deepseek-r1",
    messages=[
        {"role": "user", "content": "Prove that sqrt(2) is irrational"}
    ],
    extra_body={"thinking": {"type": "enabled"}},
    max_tokens=4096
)
# R1 returns reasoning in response.choices[0].message.reasoning_content

DeepSeek V4 vs V3 vs R1

Common Use Cases

Frequently Asked Questions