Zed (gateway)

Route Zed ’s agent and assistant requests through the Respan gateway for automatic logging, caching, and model switching. Zed supports OpenAI-compatible providers in settings.json, so only your RESPAN_API_KEY is needed.

Paste this into your coding agent:


Help me set up the Respan gateway with the Zed integration.
Follow https://www.respan.ai/docs/integrations/gateway/zed.md

Setup

Add Respan as a provider

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

JSON


{
  "language_models": {
    "openai_compatible": {
      "respan": {
        "api_url": "https://gateway.respan.ai",
        "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.

Switch models

Add more entries to available_models to use any of the 1000+ models available through the gateway.


gpt-4o
claude-sonnet-4-5-20250929
gemini/gemini-3.5-flash

See the full model list .