Integration guide · Personal agent

OpenClaw on EU-hosted open models

Add Frontière AI as a custom model provider in openclaw.json and run your self-hosted OpenClaw agents on EU-hosted open models. models.providers in ~/.openclaw/openclaw.json, with api: openai-completions; the default model in agents.defaults.model.primary.

Settings from the official documentation, checked on 12 October 2026. Not run end to end by us.

API format

OpenAI-compatible

Base URL

https://getfrontiereai.eu/api/v1

Where it goes

models.providers in ~/.openclaw/openclaw.json, with api: openai-completions; the default model in agents.defaults.model.primary.

Your prompts

Straight from your machine to us

Setup

// ~/.openclaw/openclaw.json
{
  agents: { defaults: { model: { primary: "frontiere/glm-5.2" } } },
  models: {
    mode: "merge",
    providers: {
      frontiere: {
        baseUrl: "https://getfrontiereai.eu/api/v1",
        apiKey: "${FRONTIERE_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "glm-5.2",
            name: "GLM 5.2",
            reasoning: true,
            input: ["text"],
            contextWindow: 256000,
            compat: { supportsUsageInStreaming: true },
          },
        ],
      },
    },
  },
}

Which model to pick

24 live models have tool calling measured by a real call through the gateway. Models labeled EU sovereign run at European providers; fast-access models are served through US-controlled infrastructure. Prices are per 100,000 tokens, margin and VAT included.

Good to know

• OpenClaw is a tool-using agent: keep to models with measured tool calling.
• Mark vision models with input: ["text", "image"], or attachments are passed as text references only.
• Model references take the form provider/model, e.g. frontiere/glm-5.2, also in /model inside a chat.

Where your prompts go

OpenClaw is self-hosted: your Gateway calls the configured baseUrl directly, with no relay through OpenClaw's own servers.

On our side, a model labeled EU sovereign runs at a European provider, and the gateway itself runs in Paris on Vercel, a US company — our privacy page says so. Billing keeps the model, the token counts and the amount, never the prompt or the reply.

Sovereignty →Privacy →

Sources

Official documentation, checked on 12 October 2026:

• OpenClaw — Custom model providers
• OpenClaw — Custom providers config

FAQ

Other guides

• gooseDesktop and CLI agent
• Hermes AgentPersonal agent