GatewayCoding Agents

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.

Setup

1

Install OpenClaw

$npm install -g openclaw@latest
2

Add Respan as a custom provider

Edit ~/.openclaw/openclaw.json and define a Respan-backed model under agents.defaults:

1{
2  agents: {
3    defaults: {
4      model: {
5        primary: "respan/gpt-4o"
6      },
7      models: {
8        "respan/gpt-4o": {
9          alias: "Respan Gateway",
10          provider: "custom",
11          baseUrl: "https://api.respan.ai/api",
12          apiKey: "${RESPAN_API_KEY}"
13        }
14      }
15    }
16  }
17}

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

$RESPAN_API_KEY=YOUR_RESPAN_API_KEY

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

3

Run OpenClaw

$openclaw

All LLM calls now route through Respan.

Switch models

Add more entries under models and change model.primary to use any of the 250+ models available through the gateway.

1model: {
2  primary: "respan/gpt-4o"
3  // primary: "respan/claude-sonnet-4-5-20250929"
4  // primary: "respan/gemini-3.5-flash"
5}

See the full model list.