Synap

Use Synap, Linkrra's inference API, in Dify: open-weight chat models with tool calling for agents and workflows.

Synap serves an OpenAI-compatible API at . This plugin points Dify at it, so you don't need to configure a generic OpenAI-compatible provider by hand.

Setup

Sign in at pool.linkrra.com/ai and generate an API key.
In Dify, install Synap from the Marketplace.
Go to Settings → Model Provider → Synap, paste the API key and save. Dify validates the key with one short request.

Usage

The models below appear in every model picker: LLM nodes, chatflows and agents.

Agents and tools: every listed model supports tool calling.
Other models: Synap's served catalog changes with available compute. To use a model that isn't listed, choose Add Model, enter its ID exactly as returns it, and set its context size and tool calling option.

Model	Context
	32K
	64K
	32K
	128K
	32K

Model IDs, context sizes and prices above were read from the live feed on 2026-10-24.

Credentials

One Synap API key. Dify stores it encrypted and sends it as a Bearer token on each request.

Connection requirements

Your Dify instance needs outbound HTTPS access to (port 443). No other endpoint is called.

Source and support

Source repository: https://github.com/jimmyplup/dify-synap
Issues: https://github.com/jimmyplup/dify-synap/issues
Contact: [email protected]
Privacy: PRIVACY.md