Zed (gateway)

Add Respan as a provider

Open your Zed settings (zed: open settings) and add an openai_compatible provider:

{
  "language_models": {
    "openai_compatible": {
      "respan": {
        "api_url": "https://api.respan.ai/api/v1",
        "available_models": [
          {
            "name": "gpt-4o",
            "display_name": "GPT-4o via Respan",
            "max_tokens": 128000,
            "capabilities": { "tools": true, "images": true }
          },
          {
            "name": "claude-sonnet-4-5-20250929",
            "display_name": "Claude Sonnet 4.5 via Respan",
            "max_tokens": 200000,
            "capabilities": { "tools": true, "images": true }
          }
        ]
      }
    }
  }
}

Zed appends /chat/completions to api_url, so keep the /v1 suffix.

Enter your API key

Open the Agent Panel, click the settings icon, find the respan provider, and paste YOUR_RESPAN_API_KEY. Zed also reads it from the RESPAN_API_KEY environment variable, which it derives from the provider name. Do not put the key in settings.json.

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

Pick a model

Open the model picker in the Agent Panel and select one of the models you listed under respan. All LLM calls now route through Respan.