Connect your app

OpenCode

1. Create a key on the API keys page.
2. Add the provider below to opencode.json in your project folder, or globally to ~/.config/opencode/opencode.json.
3. Put the key into the environment variable AILOCAL_API_KEY, or paste the key itself into apiKey.
4. Start opencode, run /models and choose glm-5.3-flash-uncensored.

{
  "provider": {
    "ailocal": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AILocal",
      "options": {
        "baseURL": "https://95-211-44-204.sslip.io/v1",
        "apiKey": "{env:AILOCAL_API_KEY}"
      },
      "models": {
        "glm-5.3-flash-uncensored": {
          "name": "GLM 5.3 Flash Uncensored",
          "limit": { "context": 1048576, "output": 16384 }
        }
      }
    }
  }
}

Cursor

1. Open Cursor Settings → Models.
2. Under API Keys, turn on OpenAI API Key and paste your key.
3. Turn on Override OpenAI Base URL and enter https://95-211-44-204.sslip.io/v1.
4. Click + Add model, enter glm-5.3-flash-uncensored and turn it on. Leave the Anthropic and Google fields empty.
5. Choose glm-5.3-flash-uncensored in the chat or agent model list.

Cursor sends requests through its own servers, so it needs a public address like ours; localhost does not work.

Cline (VS Code)

1. Open the Cline panel in VS Code and click the gear icon.
2. Set API Provider to OpenAI Compatible.
3. Base URL: https://95-211-44-204.sslip.io/v1. API Key: your key. Model ID: glm-5.3-flash-uncensored.
4. In Model Configuration set Context Window to 1048576 and Max Output Tokens to 16384, then click Done.

Roo Code (VS Code)

1. Open the Roo Code panel in VS Code, then Settings → Providers.
2. Set API Provider to OpenAI Compatible.
3. Base URL: https://95-211-44-204.sslip.io/v1. API Key: your key. Model: glm-5.3-flash-uncensored.
4. Set Context Window to 1048576 and Max Output Tokens to 16384. Turn on image support if you send screenshots.

Continue (VS Code, JetBrains)

1. Open the Continue config file config.yaml with the gear icon in the Continue panel.
2. Add the model below to models and save. It appears in the Continue model list.

models:
  - name: GLM 5.3 Flash Uncensored
    provider: openai
    model: glm-5.3-flash-uncensored
    apiBase: https://95-211-44-204.sslip.io/v1
    apiKey: sk-...
    defaultCompletionOptions:
      maxTokens: 16384

ZCode

1. Open Settings → Model Settings and click Add Provider at the bottom of the list.
2. Choose the OpenAI type, set Base URL to https://95-211-44-204.sslip.io/v1, the format to Chat Completions, and paste your key.
3. Click Add Model and enter the ID glm-5.3-flash-uncensored.
4. In Advanced set Context Window to 1048576 and Max Output to 16384.
5. Turn on the provider and the model.

Zed

1. Run zed: open settings file and add the block below.
2. Run agent: open settings, find OpenAI and paste your key.
3. Choose glm-5.3-flash-uncensored in the Agent panel.

{
  "language_models": {
    "openai": {
      "api_url": "https://95-211-44-204.sslip.io/v1",
      "available_models": [
        { "name": "glm-5.3-flash-uncensored", "max_tokens": 1048576, "max_output_tokens": 16384 }
      ]
    }
  }
}

JetBrains AI Assistant

1. Open Settings → Tools → AI Assistant → Providers & API keys.
2. Under Third-party AI providers choose OpenAI-compatible, enter the URL https://95-211-44-204.sslip.io/v1, paste your key and click Test Connection.
3. Choose glm-5.3-flash-uncensored in AI Chat. In Model Assignment set the context to 1048576.

Aider

1. Set two environment variables and start aider with the model name prefixed by openai/.

export OPENAI_API_BASE=https://95-211-44-204.sslip.io/v1
export OPENAI_API_KEY=sk-...
aider --model openai/glm-5.3-flash-uncensored

SillyTavern

1. Open API Connections and choose Chat Completion.
2. Set the source to Custom (OpenAI-compatible).
3. Custom Endpoint: https://95-211-44-204.sslip.io/v1. API Key: your key. Click Connect and choose glm-5.3-flash-uncensored.

Open WebUI, Cherry Studio, LobeChat, Chatbox

1. Add a provider of the OpenAI (OpenAI-compatible) type.
2. Base URL: https://95-211-44-204.sslip.io/v1. API Key: your key. Add the model glm-5.3-flash-uncensored.