How to Use DeepSeek API with LangChain

Base URL

https://modelrelayapis.cc/v1

Available Models

• deepseek-v4-flash ? Fast, affordable (Trial / Starter / Standard / Pro)
• deepseek-v4-pro ? Higher quality (all plans)

Setup Steps

1. Install the LangChain OpenAI package: pip install langchain-openai
2. Configure ChatOpenAI with our gateway as shown in the Python example below.
3. Set base_url to https://modelrelayapis.cc/v1.
4. Set api_key to your sk-gateway API Key.
5. Set model to deepseek-v4-flash.

Python Example (LangChain)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://modelrelayapis.cc/v1",
    api_key="sk-gateway-YOUR-KEY",
    model="deepseek-v4-flash"
)

response = llm.invoke("Explain quantum computing in one sentence.")
print(response.content)

Quick curl Test

curl https://modelrelayapis.cc/v1/chat/completions   -H"Content-Type: application/json"   -H"Authorization: Bearer sk-gateway-YOUR-KEY"   -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello"}]}'

Common Errors