Use Wally's fast open-weight models in Dify: chat models with tool calling for agents and workflows, reasoning, and image input on DeepSeek V4.1 Flash, DeepSeek V4.1 Flash (Fast) and Kimi K3.
Wally serves an OpenAI-compatible API at https://inference.runanywhere.ai/v1. This plugin points Dify at it, so you don't need to configure a generic OpenAI-compatible provider by hand.
- Sign in to the RunAnywhere console and create a Wally API key (
sk-runa-...). - 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.
The models below appear in every model picker: LLM nodes, chatflows and agents.
| Model | Context | Max output | Image input |
|---|---|---|---|
glm-5.3-flash (GLM-5.3 Flash) |
1M | 131,072 | no |
deepseek-v4.1-flash (DeepSeek V4.1 Flash) |
1M | 65,536 | yes |
kimi-k3 (Kimi K3) |
1M | 65,536 | yes |
deepseek-v4.1-flash-fast (DeepSeek V4.1 Flash (Fast)) |
1M | 65,536 | yes |
glm-5.3-fast (GLM-5.3 (Fast)) |
1M | 131,072 | no |
deepseek-v4-pro-fast (DeepSeek V4 Pro (Fast)) |
1M | 65,536 | no |
deepseek-v4-flash-0731 (DeepSeek V4 Flash 0731) |
1M | 65,536 | no |
minimax-m3 (MiniMax M3) |
512K | 131,072 | no |
- Agents and tools: all eight models support tool calling, including parallel and streamed tool calls.
- Reasoning: Dify shows the model's reasoning as a collapsible thought. Set Reasoning effort in the model parameters to choose how much the model thinks, or leave it empty for the model default.
- GLM-5.3 Flash, GLM-5.3 (Fast) and MiniMax M3 always think; the lowest level is
minimalon GLM-5.3 Flash andlowon the other two. - DeepSeek V4.1 Flash, DeepSeek V4.1 Flash (Fast) and Kimi K3 think by default;
noneturns thinking off. - DeepSeek V4 Pro (Fast) and DeepSeek V4 Flash 0731 don't think unless you pick a level.
- GLM-5.3 Flash, GLM-5.3 (Fast) and MiniMax M3 always think; the lowest level is
- Structured output: set Response Format to
json_object, or tojson_schemaand paste a JSON schema. - Other models: to use a Wally model that isn't listed yet, choose Add Model, enter its ID exactly as
GET https://inference.runanywhere.ai/v1/modelsreturns 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.
One Wally API key. Dify stores it encrypted and sends it as a Bearer token on each request.
Your Dify instance needs outbound HTTPS access to inference.runanywhere.ai (port 443). No other endpoint is called.
- Source repository: https://github.com/RunanywhereAI/wally-dify-plugin
- Issues: https://github.com/RunanywhereAI/wally-dify-plugin/issues
- Contact: support@runanywhere.ai
- Privacy: PRIVACY.md