Integrations OpenClaw
Use DeepSeek in OpenClaw, hosted in Australia
Add the Xinference Model API to OpenClaw as a custom provider and run DeepSeek V4.1 Flash or GLM-5.3 in Australian data centres.
Set it up in four steps
- 1
Get your key
Sign up for the Model API and create an API key in the console.
- 2
Run onboarding
Run this and pick Custom provider. Paste your API key when asked.
$ openclaw onboard - 3
Enter your details
Use these values. OpenClaw names models as provider and model ID, so keep the provider ID short.
Base URL https://cloud.xinference.co/v1 Model ID deepseek-v4.1-flash Provider ID xinference - 4
Set the default model
Make DeepSeek the default. To switch in a chat, type
/model xinference/glm-5.3.$ openclaw models set xinference/deepseek-v4.1-flash
Prefer a config file?
Add the provider to ~/.openclaw/openclaw.json.
{
agents: { defaults: { model: { primary: "xinference/deepseek-v4.1-flash" } } },
models: {
mode: "merge",
providers: {
xinference: {
baseUrl: "https://cloud.xinference.co/v1",
apiKey: "${XINFERENCE_API_KEY}",
api: "openai-completions",
models: [
{ id: "deepseek-v4.1-flash", name: "DeepSeek V4.1 Flash" },
{ id: "glm-5.3", name: "GLM-5.3" },
],
},
},
},
}


