Connect OpenClaw
Register UNST33R as a custom OpenAI-compatible provider, then make one of the three public model ids your primary model.
01
Create a key
Sign in to the UNST33R console and create an API Key. Keep the key out of the configuration file.
02
Expose the key to OpenClaw
export UNST33R_API_KEY="<your-api-key>"
Set this in the environment used to start the OpenClaw Gateway. Do not commit it.
03
Add the provider
// ~/.openclaw/openclaw.json
{
agents: {
defaults: {
model: { primary: "unst33r/unst33r-flash" },
},
},
models: {
mode: "merge",
providers: {
unst33r: {
baseUrl: "https://api.unst33r.si/v1",
apiKey: "${UNST33R_API_KEY}",
api: "openai-completions",
models: [
{ id: "unst33r-flash", name: "UNST33R Flash" },
{ id: "unst33r-deepseek", name: "UNST33R DeepSeek" },
{ id: "unst33r-pro", name: "UNST33R Pro" },
],
},
},
},
}The Base URL already includes /v1. Do not append it again.
04
Validate and switch models
openclaw doctor # In OpenClaw, use one of these model references: unst33r/unst33r-flash unst33r/unst33r-deepseek unst33r/unst33r-pro