Wally

Use Wally's fast open-weight models in Dify: chat models with tool calling for agents and workflows, reasoning, and image input on GLM-5.3 Flash and DeepSeek V4.1 Flash.

Wally 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 to the RunAnywhere console and create a Wally API key ().
In Dify, install Wally from the Marketplace.
Go to Settings → Model Provider → Wally, paste the API key and save. Dify checks the key with one short request.

Usage

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

Model	Context	Max output	Image input
(GLM-5.3 Flash)	1M	131,072	yes
(DeepSeek V4.1 Flash)	1M	262,144	yes
(MiMo V2.6 Pro)	1M	131,072	no

Agents and tools: all three models support tool calling, including parallel and streamed tool calls.
Thinking mode: on by default. The model reasons first and Dify shows the reasoning as a collapsible thought. Turn Thinking mode off in the model parameters for faster, shorter replies.
Reasoning effort: GLM-5.3 Flash and DeepSeek V4.1 Flash accept , or . MiMo V2.6 Pro has thinking on or off only.
Structured output: set Response Format to , or to and paste a JSON schema.
Other models: to use a Wally model that isn't listed yet, choose Add Model, enter its ID exactly as returns it, and set its context size, tool calling and image input options.

Prices are on runwally.com/pricing. API reference: docs.runanywhere.ai/wally-cloud/api.

Credentials

One Wally 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/RunanywhereAI/wally-dify-plugin
Issues: https://github.com/RunanywhereAI/wally-dify-plugin/issues
Contact: [email protected]
Privacy: PRIVACY.md