OpenClaw (gateway)

Route OpenClaw ’s LLM calls through the Respan gateway for automatic logging, caching, and model switching. OpenClaw supports custom OpenAI-compatible providers, so only your RESPAN_API_KEY is needed.

Paste this into your coding agent:


Help me set up the Respan gateway with the OpenClaw integration.
Follow https://www.respan.ai/docs/integrations/gateway/open-claw.md

Setup

Install OpenClaw

Terminal


npm install -g openclaw@latest

Add Respan as a custom provider

Edit ~/.openclaw/openclaw.json and define a Respan provider under models.providers, then make it the default model:

JSON5


{
  models: {
    providers: {
      respan: {
        baseUrl: "https://gateway.respan.ai",
        apiKey: "${RESPAN_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "gpt-4o",
            name: "GPT-4o",
            reasoning: false,
            input: ["text", "image"],
            cost: { input: 2.5, output: 10, cacheRead: 1.25, cacheWrite: 0 },
            contextWindow: 128000,
            maxTokens: 16384,
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "respan/gpt-4o" },
    },
  },
}

Set RESPAN_API_KEY in your shell or in ~/.openclaw/.env:

Terminal


RESPAN_API_KEY=YOUR_RESPAN_API_KEY

No separate provider key needed. The Respan gateway handles provider authentication.

Run OpenClaw

Terminal


openclaw

To check the routing with a single local turn:

Terminal


openclaw agent --local -m "your prompt"

All LLM calls now route through Respan.

Switch models

Add more entries under models and change model.primary to use any of the 1000+ models available through the gateway.

JSON5


model: {
  primary: "respan/gpt-4o",
  // primary: "respan/claude-sonnet-4-5-20250929"
  // primary: "respan/gemini/gemini-3.5-flash"
}

See the full model list .