Run OpenClaw on one endpoint with a hard spend cap
OpenClaw is an autonomous agent CLI, and long agent sessions burn tokens fast — often unattended. Registering Router One as its custom OpenAI-compatible provider puts every model call on one key you can cap: set maxSpend on the key and a runaway session stops at the cap instead of draining your wallet. Every call is traced for cost, and when an upstream returns a retryable 5xx or timeout, the request may be retried on the next healthy provider serving that same model — useful when a session runs for hours.
Configure OpenClaw to use the Router One base URL
Run OpenClaw's onboarding with a custom OpenAI-compatible provider pointing at the gateway — the CLI setup guide walks through the same flow step by step for macOS, Windows, and Linux:
export CUSTOM_API_KEY=sk-your-router-one-key openclaw onboard --non-interactive \ --auth-choice custom-api-key \ --custom-base-url https://api.router.one/v1 \ --custom-model-id gpt-5.5 \ --custom-provider-id router-one \ --custom-compatibility openai \ --install-daemon
Which model ID should OpenClaw send?
Copy the exact model ID from the /models page — IDs are case-sensitive, and the page lists each model's context window, capabilities, and current per-token rates. Create a dedicated API key per tool with its own maxSpend cap, so one runaway tool can't affect other workloads.
Verify the OpenClaw call in your request trace
After your first request, open Dashboard → Logs to see its full trace: model, tokens, cost, latency, and status code. From here every OpenClaw call has a ledger and a trail instead of being a black box.
FAQ
How do I keep an OpenClaw session from overrunning its budget?
Create a dedicated API key for OpenClaw and set a maxSpend hard cap on it — when the key hits its cap it stops, and your wallet and other keys are untouched. Dashboard → Logs shows the per-request cost trace, so you can see what each session actually spent.
Which models can OpenClaw use through the gateway?
Any chat-capable model in the catalog — GPT, Claude, Gemini, Grok, DeepSeek, GLM, and Kimi families. The /models page is the source of truth for model IDs and per-token rates.
Does this work from Mainland China?
Yes. The gateway is reachable from Mainland China without a VPN, and the configuration is identical to the global setup.
How do I debug a 401/403/429?
Open Dashboard → Logs first to see whether requests reached the gateway and with what status, then walk the error-codes reference to check env vars, key status, and limits.