API Documentation

Welcome to the DeepSeek API documentation. Our API provides powerful AI capabilities through simple HTTP requests, enabling you to integrate advanced language model features into your applications.

Quick Start

Get started with the DeepSeek API in just a few steps:

1. Get Your API Key

First, you'll need to obtain an API key:

• Sign up for a DeepSeek account
• Navigate to the API Keys section in your dashboard
• Generate a new API key for your project

2. Make Your First Request

Here's a simple example using curl:

curl -X POST "https://api.deepseek.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ]
  }'

3. Handle the Response

The API will return a JSON response with the model's output:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

API Features

Chat Completions

• Text Generation: Generate human-like responses for conversations
• System Messages: Set context and behavior for the AI assistant
• Streaming: Real-time response streaming for better user experience
• Function Calling: Enable the model to call external functions

Multimodal Support

• Image Understanding: Process and analyze images alongside text
• Vision-Language Tasks: Combine visual and textual information
• Document Analysis: Extract information from documents and images

Advanced Features

• JSON Mode: Force structured JSON output for data extraction
• Long Context: Handle extended conversations and documents
• Batch Processing: Process multiple requests efficiently
• Custom Models: Fine-tuned models for specific use cases

Authentication

All API requests require authentication using an API key. Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Rate Limits

To ensure fair usage and optimal performance:

• Free Tier: 100 requests per minute
• Pro Tier: 1,000 requests per minute
• Enterprise: Custom limits based on your needs

Error Handling

The API uses standard HTTP status codes and returns detailed error messages:

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

SDKs and Libraries

We provide official SDKs for popular programming languages:

• Python: pip install deepseek-python
• Node.js: npm install deepseek-node
• Java: Maven and Gradle support
• Go: Go modules support
• PHP: Composer package available

Next Steps

• Authentication Guide - Detailed authentication setup
• Chat API Reference - Complete chat API documentation
• Multimodal API - Image and vision capabilities
• Models Overview - Available models and their capabilities
• Error Codes - Complete error code reference
• FAQ - Frequently asked questions

Support

Need help? We're here to assist:

• Documentation: Comprehensive guides and examples
• Community: Join our developer community
• Support: Contact our technical support team
• Status: Check our API status and uptime

---

Ready to build something amazing? Start with our Quick Start Guide or explore our Use Cases for inspiration.