Dify Integration

Dify is a low-code platform for building AI-powered applications with workflow automation, RAG pipelines, and agent capabilities. It supports a wide range of model providers and allows workspace administrators to manage API keys and model access centrally.

Dify's Model Providers feature supports OpenAI-compatible APIs, allowing you to add LLM API as a custom provider for all your Dify applications.

Prerequisites

An LLM API account with an API key
Dify installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Add LLM API as a Model Provider in Dify

Log in to your Dify workspace as an admin or owner.
Navigate to Settings → Model Providers.
Find "OpenAI-API-compatible" in the provider list and click to configure.
Enter the following details:
- Model Name: the model ID you wish to use (e.g., openai/gpt-4o)
- API Key: paste the key you copied from app.llmapi.ai/api-keys
- API Endpoint URL: https://api.llmapi.ai/v1
Click "Save" --- Dify will validate the credentials before enabling the provider.
The model will now be available for selection in your Dify applications.

Test the Integration

Verify that Dify can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

You can add multiple model configurations under the same provider. Each can use a different model ID while sharing the same LLM API key and endpoint.

Benefits of Using LLM API with Dify

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

View all available models on the models page.