Integrations

Zed

Code editor with a built-in AI agent panel. Step-by-step setup with Laras Router.

On this page

This guide connects Zed to Laras Router. Every step was checked against the Zed documentation.

You need an API key (lr_live_…) and a topped-up balance. New to Laras Router? Start with the Quickstart.

Set up

Add the provider

Run agent: open settings and click Add Provider under LLM Providers, or add the provider to your settings.json.

settings.json
{
  "language_models": {
    "openai_compatible": {
      "laras-router": {
        "api_url": "https://api.larasrouter.com/v1",
        "available_models": [
          {
            "name": "deepseek-flash",
            "display_name": "DeepSeek Flash (Laras Router)",
            "max_tokens": 1000000,
            "max_output_tokens": 32000,
            "capabilities": {
              "tools": true,
              "images": false,
              "parallel_tool_calls": false,
              "prompt_cache_key": false
            }
          }
        ]
      }
    }
  }
}

Add your API key

Add your key in the provider’s settings, where Zed stores it in the system keychain, or set the environment variable Zed derives from the provider ID.

Shell
export LARAS_ROUTER_API_KEY="lr_live_your_key_here"

Pick the model

Pick DeepSeek Flash (Laras Router) in the agent panel’s model selector.

Good to know

  • Do not put the key in settings.json.
  • Zed sends the output limit as max_completion_tokens, which Laras Router accepts in place of max_tokens.

Settings and screens can change between versions. If something looks different, check the Zed documentation. For other tools, see all integrations.