Dify integration
Use DeepSeek in Dify with an OpenAI-Compatible Model Provider
Dify supports custom OpenAI-compatible model providers. Add Tokuse once, then choose the DeepSeek model inside each app or workflow instead of hard-coding credentials in prompts.
Settings
- Provider
- OpenAI-API-compatible
- Base URL
- https://tokuse.com/v1
- Model name
- deepseek-flash
- API key
- Your Tokuse key
Setup steps
- Open Settings, then Model Provider, then OpenAI-API-compatible.
- Set the Base URL to https://tokuse.com/v1 without appending /chat/completions.
- Paste a Tokuse API key into the provider configuration.
- Add deepseek-flash as a model; add deepseek-v4-pro only for tasks that need it.
- Run a one-node test workflow before publishing the app.
Before production use
- Keep the Tokuse key on the server or in the tool's secret store.
- Use the base URL without appending /chat/completions.
- Verify the model alias in the current Tokuse catalog.
- Test errors, timeout behavior, and cost with a small workload first.