DeepSeek API integration - Access DeepSeek V3, DeepSeek Coder models through UniterRouter. OpenAI-compatible format for seamless migration from ChatGPT.

DeepSeek API

Access DeepSeek models through UniterRouter using the OpenAI-compatible API format. DeepSeek offers powerful reasoning and coding models at competitive prices.

DeepSeek-R1: The reasoning model provides extended thinking capabilities with visible reasoning chains.

Quick Start

curl https://api.uniterouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $UNITEROUTER_API_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ]
  }'

from openai import OpenAI

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

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.uniterouter.ai/v1",
  apiKey: process.env.UNITEROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [
    { role: "user", content: "Explain quantum computing" }
  ],
});
console.log(response.choices[0].message.content);

Available Models

Model	Description	Context	Best For
`deepseek-chat`	General chat model	64K	Conversations, Q&A
`deepseek-coder`	Code-specialized model	64K	Coding, debugging
`deepseek-reasoner`	Reasoning model (R1)	64K	Complex reasoning, math

DeepSeek Reasoner (R1)

The DeepSeek Reasoner model provides visible reasoning chains:

response = client.chat.completions.create(
    model="deepseek-reasoner",
    messages=[
        {"role": "user", "content": "Solve: What is 15% of 240?"}
    ]
)

# The response includes reasoning in the content
print(response.choices[0].message.content)

Reasoning Output

The model's response includes its reasoning process:

Let me think through this step by step:
1. 15% means 15/100 = 0.15
2. 240 × 0.15 = 36

Therefore, 15% of 240 is 36.

Coding Tasks

DeepSeek excels at coding tasks:

response = client.chat.completions.create(
    model="deepseek-coder",
    messages=[
        {"role": "system", "content": "You are an expert programmer."},
        {"role": "user", "content": "Write a Python function to find the nth Fibonacci number using memoization"}
    ]
)

Streaming

Enable streaming for real-time responses:

stream = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Write a poem about AI"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Features

Long Context: Up to 64K tokens context window
Reasoning: Extended thinking with visible chains
Code Generation: Excellent at writing and debugging code
Math: Strong mathematical reasoning capabilities
Multilingual: Supports multiple languages including Chinese

Pricing

DeepSeek models are known for competitive pricing. Check the models page for current rates.

Chat Completions - Full API documentation
Reasoning - Extended thinking guide

DeepSeek

On this page