Zed

Expose LLMRPM models in Zed's assistant model picker.

Configuration

Setting	Value
API shape	OpenAI-compatible
Base URL	`https://llmrpm.com/api/v1`
Auth	`Authorization: Bearer llmrpm_...`

Open Zed settings and configure the openai language model provider.
Set api_url to https://llmrpm.com/api/v1.
Add the public model IDs you want exposed in the model picker.
Set the API key through Zed secrets or your environment.

Example

settings.json

{
  "language_models": {
    "openai": {
      "api_url": "https://llmrpm.com/api/v1",
      "available_models": [
        {
          "name": "claude-sonnet-5",
          "display_name": "LLMRPM Sonnet",
          "max_tokens": 200000
        }
      ]
    }
  }
}

Recommended models

Any public ID from the model list works. Common picks:

claude-sonnet-5— strong model for reasoning, refactors, and coding agents.
claude-haiku-4.5— fast option for autocomplete, small questions, and lightweight tasks.
deepseek-v4-pro— alternative based on your active catalog and plan.

Troubleshooting

Symptom	Cause & fix
Authentication error	Check that the API key has no extra spaces and has not been revoked in the dashboard.
Model rejected	Use a public model ID returned by GET /api/v1/models; do not use display names or aliases.
Connection issue	Confirm the configured base URL is exactly the one shown above and that your network allows HTTPS to llmrpm.com.

Notes

If Zed does not list the model, verify the name exactly matches a public ID from /api/v1/models.
Use a lower-latency model for inline edits and a stronger model for planning.

PreviousAider Next JetBrains