> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Zed setup

> Use a Pearl model in the Zed editor and its agent.

## Before you start

Complete organization setup, make sure your account has inference credit, and create a key on the [API Keys page](https://platform.pearlresearch.ai/api-keys). Most coding agents need a tool-capable chat model; Aider's basic edit workflow does not require native tool calling. Image input and reasoning support depend on the model. These terminal examples use Bash or Zsh on macOS, Linux, or Windows through WSL.

Install Zed and use a version with Anthropic-compatible custom providers. [Installation instructions](https://zed.dev/docs/installation).

## Get your connection settings

Open [Integrations](https://platform.pearlresearch.ai/integrations), select a model, then choose Zed. The screen uses your organization's region. The examples below use the public global endpoint; replace it with your regional endpoint and replace `YOUR_MODEL_ID` with the full model ID shown there. Choose one of the models listed for this integration.

Paste your Pearl API key into Zed's API key field. Enter the key itself, not an environment variable name.

## Configure Zed

Merge the language\_models.anthropic\_compatible.Pearl entry into your Zed settings. Enter the Pearl key in the provider's secure API key field. The URL is the endpoint origin without /v1. Context, output, image, and tool capabilities come from the selected model.

```json Zed settings.json (merge language_models) theme={null}
{
  "language_models": {
    "anthropic_compatible": {
      "Pearl": {
        "api_url": "https://inference.pearlresearch.ai",
        "available_models": [
          {
            "name": "YOUR_MODEL_ID",
            "display_name": "YOUR_MODEL_ID",
            "max_tokens": 131072,
            "max_output_tokens": 8192,
            "capabilities": {
              "tools": true,
              "images": false,
              "prompt_caching": false
            }
          }
        ]
      }
    }
  }
}
```

```text Connect in Zed theme={null}
Open Settings → AI → LLM Providers.
Find Pearl and enter your Pearl API key in its secure key field.
Open the Agent Panel and select Pearl / YOUR_MODEL_ID.
Start a new conversation.
```

## Start using Zed

Open the Agent Panel, select the Pearl model, and start a new conversation. Ask it to explain a file or make a small change. Approve file or terminal actions as appropriate for your project.

## Troubleshooting

Choose a Pearl chat model with tool calling. Pearl chat models support all three API formats; this setup uses Anthropic Messages. Keep prompt\_caching false unless the gateway explicitly supports those markers. The example config sets max\_tokens, Zed's context window, to 131072, which fits every current Pearl chat model. The Integrations page fills in the selected model's own context window.

* `401`: check the key and allow time for a newly created key to reach the inference gateway.
* `404`: copy the endpoint and exact model ID from Integrations. OpenAI base URLs end in `/v1`; the Anthropic SDK and Claude Code use the URL without that suffix.
* `402`: check your organization's credit and billing status.
* `429` or Anthropic `529`: respect retry instructions and reduce concurrency.
* For truncated output, check the output limit and reasoning budget. Increase limits only within the model's maximum output length.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.