SoduWork Custom Model Setup: Connect an OpenAI-Compatible Gateway and Handle the 180-Second Stall

2026-11-16来源 dev.to AIEnglish
SoduWork Custom Model Setup: Connect an OpenAI-Compatible Gateway and Handle the 180-Second Stall

SoduWork custom model setup with an OpenAI-compatible gateway

You install SoduWork, open the chat, and the model picker is empty. What is missing?

A model service. SoduWork is an agent workbench that ships without a language model, so it only works after you connect one. On November 16, 2026, I connected an OpenAI-compatible gateway to SoduWork v1.13.16 on Windows, and both gpt-6-sol and claude-haiku-5-5 appeared in the picker. The short version: add a service under My models, give it an API URL ending in /v1, set the protocol to OpenAI compatible, paste a key, and register each Model ID by hand. This post is for developers who already have an API key and want to switch models inside SoduWork. If your team already provides a preconfigured gateway, skip to the last section on a 180-second stall I hit during a chat.

What you need before starting

Item What I used
SoduWork v1.13.16, Windows
Protocol OpenAI compatible
API URL the gateway Base URL, ending in /v1
Credentials a personal API key
Models gpt-6-sol, claude-haiku-5-5
Checked on November 16, 2026

Get the client

The official site is soduwork.ai, and installers live on the Releases page of mdiri-ai/SoduWork. At the time of writing, the latest release contained only the Windows installer, SoduWork-1.13.16-Setup.exe; check Releases for other platforms. Forks with the same name exist, so use the official site or that exact repository.

Create the key

SoduWork does the work and an external model does the thinking, so you need an endpoint first. I used Crazyrouter, where one key reaches models from several vendors. The integration guide shows how the Base URL is written.

  1. Sign in and open Console.
  2. On the Overview page, read the API address in API Info.
  3. Click Create API Key, or go through API Keys in the sidebar.
  4. Copy the key immediately. The full value is only shown at creation.

Console Overview page with the API address and the Create API Key button

Treat the key like a password. A partial key was visible in this screenshot, and I masked it before publishing.

Open My models and add a service

  1. Click the avatar at the bottom left.
  2. Choose My models.
  3. Click + Add service above the Model service list.

The avatar at the bottom left opens settings

My list already had a company gateway, ByteDance Volcano Ark, DeepSeek, Alibaba Cloud Bailian, Zhipu GLM, and Kimi. They use the same screen, so connecting a vendor directly follows the same steps.

Fill in the connection settings

Field Value
Service name Crazyrouter (any recognizable name)
API URL copy the line below
API protocol OpenAI compatible
No key required leave unchecked
https://api.crazyrouter.com/v1 

The trailing /v1 is the part that gets forgotten. Before a key is pasted, Connection status reads Verification failed, which is just the initial state.

My models page with service name, API URL, and API protocol

Paste the key into Personal API key under Access credentials and click Save and test connection. When the status becomes Connection verified, click Save.

Register each model by hand

A verified connection means the service is reachable, nothing more. Model count was still 0. Where do the IDs come from?

I used the Model Square on the Crazyrouter site, which listed 173 models with vendor and type filters. The model catalog works for checking names as well. In SoduWork:

Field Value
Model ID the exact catalog name, such as gpt-6-sol
Display name same as the ID, or any label you prefer
Model purpose Chat model
Reasoning mode left on Auto detect
Model capabilities image input, tool call, and streaming were all Supported for me

A single wrong character in the Model ID makes calls fail, so copy the name instead of retyping it.

Copying a name from the model catalog into Model ID and Display name

Save, then repeat for claude-haiku-5-5. One gateway now exposes models from two vendors.

Pick a model in a new chat

Click New chat, then the model name at the bottom right of the input box to open Choose a model. Both models show their source as Crazyrouter · Personal quota.

Choose a model window listing two models from Crazyrouter

The Reasoning mode at the bottom of that window said Unsupported for gpt-6-sol; I left it alone. The company gateway's glm-5.3-flash appeared in the same list, so models from different sources can be mixed.

The 180-second stall

During a chat, a task stopped partway with a notice that 180 seconds had passed. From what I could check, the limit is a fixed threshold built into the app. My models has no matching option, and changing the gateway does not move it.

What I would do about it:

  • Split large tasks so the model produces output sooner.
  • Reserve slow, heavy-reasoning models for tasks that need them.
  • Keep Streaming on Supported, which was my default. I did not test whether it prevents the stall.
  • After an interruption, send "continue" in the same conversation.

Quick troubleshooting

Symptom Check first
Verification failed URL ends in /v1, protocol is OpenAI compatible, key pasted in full, account has balance
Model missing from the picker Model ID matches the catalog exactly, Save was clicked
A chat call fails Re-copy the Model ID, confirm personal quota remains
Another vendor needed Add a second service in My models

This covers only what I verified: the setup flow and model selection on SoduWork v1.13.16 for Windows. I did not benchmark how each model handles long tasks inside SoduWork. If you have connected several models, has the 180-second limit ever stopped one of your sessions?

References: SoduWork official site and SoduWork GitHub Releases.

原文:https://www.a8q9.cn/en/article/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the--df3f7b.html

相关文章