Use Scenepond in Dify

Build a chat assistant, knowledge-based Q&A, or an agent with an enabled OpenAI-compatible chat model.

1. In Dify, install the OpenAI-API-compatible model provider from Integrations or Marketplace, then select Add Model and the LLM type.
2. Copy the exact model ID from the catalog and enter the following provider settings.

Model Name

deepseek-v4-pro Choose a model ↗

API Key

Your Scenepond API key, without the Bearer prefix

API Base URL

https://scenepond-api-production.up.railway.app/v1

Completion mode

Chat

API Type

Chat Completions API

If Dify asks for context size or an output-token limit, use verified model information. Enable vision, tools, streaming, or structured output only when the selected model supports them.

Use the /v1 base URL here, without /chat/completions. This setup covers chat models; it does not configure image or video generation.