OpenClaw Integration

Prepare in the dashboard

Sign in to dashboard.koboillm.com with your email and password, then select your team at the top.
Open API Keys → Create API key. Enter a Key name; the key budget is optional. The defaults are No expiry and All Team Models. Select Create and save the full key, which is shown once.
Copy an accessible model name from Model List. Choose a model that supports this guide's endpoint; API Quickstart also provides request examples.
After running your application, open Logs in the same team, select a time range, and use View details on a request to check its key, tokens, and recorded spend.

OpenAI-compatible base URL: https://api.koboillm.com/v1. Follow the client-specific URL format below. The dashboard address is for your account; applications use the API key, not your account password.

Show the current key creation form

Actual dashboard interface with fictional demonstration data. Click to enlarge.

Model names and provider prices in examples are reference values. Availability, endpoint support, and final recorded costs depend on your key and request.

Older videos may show the legacy dashboard. Follow the current Dashboard Guide for account and key steps.

OpenClaw is a self-hosted AI agent platform that can be deployed on your local servers. This guide shows you how to connect OpenClaw to your KoboiLLM multi-model proxy API.

Key Benefits of Self-Hosted OpenClaw

Cost Efficient — Runs on affordable hardware such as recycled STB devices or SBCs.
24/7 Operations — Low-power consumption (12V) ideal for persistent background tasks.
Local application state — OpenClaw runs on your hardware; model requests still go through the configured API provider.
Model Agnostic — Switch between OpenAI, Gemini, and Claude models on the fly.

Prerequisites & Recommended Setup

Hardware

Armbian Linux or standard Debian/Ubuntu server.
2GB RAM minimum with ZRAM enabled.
Optional 12V Mini-UPS for power fault tolerance.

Software

SSH root access to your server.
Installed utilities: curl, git, bash.

Installation Steps

1. Update System Packages

sudo apt update && sudo apt upgrade -y

2. Run OpenClaw Installer

Run the official one-line installation script:

curl -sSfL https://openclaw.ai/install.sh | bash

3. Configure KoboiLLM Credentials

During the onboarding setup or inside your OpenClaw environment config (~/.openclaw/config.json):

Provider: OpenAI
Base URL: https://api.koboillm.com/v1
API Key: sk-xxxx
Model: openai/gpt-4o-mini or anthropic/claude-3-5-sonnet

Copy the exact model ID available to your key from Model List. The names above are examples; a model must also support OpenClaw’s required endpoint and tool calls.

Verify a request in the dashboard

After sending a message from OpenClaw, select the key’s team in the dashboard and open Logs. Select the time range and model, then choose View details to inspect the Request ID, key, token counts, and recorded spend. Open Usage for totals across the reporting period.

If a request fails, check that the key is active, has access to the selected model, and uses https://api.koboillm.com/v1. Check the team balance, key budget, and any member budget; creating another key does not reset a member’s shared spending limit. Include the Request ID and error when contacting support, and keep the full key private.