Dify + OpenBulu configuration
Choose an OpenAI-compatible provider, then enter the Base URL, key, and model ID. Test workflows and tool calls separately.
Protocol: OpenAI-compatible. Base URL: https://openbulu.com/v1. Endpoint: POST /v1/chat/completions.
Configuration reference
Provider: OpenAI-API-compatible (official plugin)
Model type: LLM
Model Name: <MODEL_ID>
API Key: <OPENBULU_API_KEY>
API Base URL: https://openbulu.com/v1
Completion mode: Chat
API Type: Chat CompletionsConfiguration and verification steps
- In Dify Model Providers, use the official OpenAI-API-compatible provider and add an LLM model. Install that provider plugin first if it is not available.
- Enter the exact OpenBulu model ID as Model Name, your API key, and https://openbulu.com/v1 as API Base URL. Choose Chat completion mode and Chat Completions API type; set context and token limits to the model’s actual capabilities.
- Save the model, select it in a basic Dify app, send a short request, and match the model and /v1/chat/completions route in OpenBulu usage logs. Verify workflow tools, streaming, and vision separately.
Use your own API key and an available model ID. Confirm the selected provider and model in the client, run a small request, and match its time, route, and model in your OpenBulu usage log. Advanced tool actions may need separate testing.