{"slug": "soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the", "title": "SoduWork Custom Model Setup: Connect an OpenAI-Compatible Gateway and Handle the 180-Second Stall", "summary": "A developer connected an OpenAI-compatible gateway (Crazyrouter) to the SoduWork agent workbench v1.13.16 on Windows, registering the model IDs gpt-6-sol and claude-haiku-5-5 by hand after adding a service with an API URL ending in /v1 and an OpenAI-compatible protocol. The setup required manually entering exact catalog model names, since a verified connection alone left the model count at zero, and the developer also reported hitting a 180-second stall during a chat.", "body_md": "You install SoduWork, open the chat, and the model picker is empty. What is missing?\n\nA 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.\n\n| Item | What I used | \n|---|---|\n| SoduWork | v1.13.16, Windows | \n| Protocol | OpenAI compatible | \n| API URL | the gateway Base URL, ending in `/v1` | \n| Credentials | a personal API key | \n| Models | `gpt-6-sol` ,`claude-haiku-5-5` | \n| Checked on | November 16, 2026 | \n\nThe official site is [soduwork.ai](https://www.soduwork.ai), and installers live on the [Releases page](https://github.com/mdiri-ai/SoduWork/releases) 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.\n\nSoduWork 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](https://crazyrouter.com/en/integrations?utm_source=devto&utm_medium=article&utm_campaign=offsite_article&utm_content=cr_ebcba2454ca1_mid_text) shows how the Base URL is written.\n\nTreat the key like a password. A partial key was visible in this screenshot, and I masked it before publishing.\n\nMy 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.\n\n| Field | Value | \n|---|---|\n| Service name | `Crazyrouter` (any recognizable name) | \n| API URL | copy the line below | \n| API protocol | `OpenAI compatible` | \n| No key required | leave unchecked | \n\n```\nhttps://api.crazyrouter.com/v1\n```\n\nThe trailing `/v1` is the part that gets forgotten. Before a key is pasted, Connection status reads **Verification failed**, which is just the initial state.\n\nPaste the key into **Personal API key** under **Access credentials** and click **Save and test connection**. When the status becomes **Connection verified**, click **Save**.\n\nA verified connection means the service is reachable, nothing more. Model count was still 0. Where do the IDs come from?\n\nI used the Model Square on the Crazyrouter site, which listed 173 models with vendor and type filters. The [model catalog](https://crazyrouter.com/en/models) works for checking names as well. In SoduWork:\n\n| Field | Value | \n|---|---|\n| Model ID | the exact catalog name, such as `gpt-6-sol` | \n| Display name | same as the ID, or any label you prefer | \n| Model purpose | Chat model | \n| Reasoning mode | left on Auto detect | \n| Model capabilities | image input, tool call, and streaming were all Supported for me | \n\nA single wrong character in the Model ID makes calls fail, so copy the name instead of retyping it.\n\nSave, then repeat for `claude-haiku-5-5`. One gateway now exposes models from two vendors.\n\nClick **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`.\n\nThe 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.\n\nDuring 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.\n\nWhat I would do about it:\n\n| Symptom | Check first | \n|---|---|\n| Verification failed | URL ends in `/v1` , protocol is OpenAI compatible, key pasted in full, account has balance | \n| Model missing from the picker | Model ID matches the catalog exactly, Save was clicked | \n| A chat call fails | Re-copy the Model ID, confirm personal quota remains | \n| Another vendor needed | Add a second service in My models | \n\nThis 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?\n\nReferences: [SoduWork official site](https://www.soduwork.ai) and [SoduWork GitHub Releases](https://github.com/mdiri-ai/SoduWork/releases).", "url": "https://wpnews.pro/news/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the", "canonical_source": "https://dev.to/buluo/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the-180-second-stall-2bno", "published_at": "2026-11-16 09:14:08+00:00", "updated_at": "2026-11-16 09:20:58.932917+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "large-language-models", "ai-products"], "entities": ["SoduWork", "Crazyrouter", "mdiri-ai", "gpt-6-sol", "claude-haiku-5-5", "ByteDance Volcano Ark", "DeepSeek", "Zhipu GLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the", "markdown": "https://wpnews.pro/news/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the.md", "text": "https://wpnews.pro/news/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the.txt", "jsonld": "https://wpnews.pro/news/soduwork-custom-model-setup-connect-an-openai-compatible-gateway-and-handle-the.jsonld"}}