Base URL

API ??

https://modelrelayapis.cc/v1

Available Models

????

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

Setup Steps

????

1. In Dify, go to Settings ? Model Providers.
2. Add a new OpenAI-API-compatible provider.
3. Set API Base URL to https://modelrelayapis.cc/v1.
4. Enter your sk-gateway API Key.
5. Add model name: deepseek-v4-flash (or deepseek-v4-pro for Pro plan).
6. Save and use in your Dify apps.

1. ? Dify ????? ? ??????
2. ?? OpenAI-API-compatible ????
3. API Base URL ?? https://modelrelayapis.cc/v1
4. ?? sk-gateway API Key?
5. ???? deepseek-v4-flash?Pro ???? deepseek-v4-pro??
6. ???? Dify ??????

Python Example

Python ??

from openai import OpenAI

client = OpenAI(
    base_url="https://modelrelayapis.cc/v1",
    api_key="sk-gateway-YOUR-KEY"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello, how are you?"}]
)

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

Quick curl Test

curl ????

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

????