OpenCode API Setup — XEDOC Provider

Connect automatically

Install Node.js 20 or later, fully quit the selected client, and run this command. The assistant checks your key, shows the files it will update, and saves a private backup before applying changes.

Windowspowershell

npx.cmd --yes https://xedoc.top/downloads/xedoc-setup-1.0.1.tgz --clients opencode

macOSbash

npx --yes https://xedoc.top/downloads/xedoc-setup-1.0.1.tgz --clients opencode

Linuxbash

npx --yes https://xedoc.top/downloads/xedoc-setup-1.0.1.tgz --clients opencode

Choose a model

#

Terminalshell

opencode

Enter /models, open XEDOC and select a model. Rerun xedoc to refresh the client’s model list when availability changes.

Configure manually

#

Merge an XEDOC provider into your global opencode.json or opencode.jsonc under ~/.config/opencode/. The installer respects XDG_CONFIG_HOME and preserves other providers.

opencode.jsonjson

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "xedoc": {
      "npm": "@ai-sdk/openai",
      "name": "XEDOC",
      "options": {
        "baseURL": "https://api.xedoc.top/v1",
        "apiKey": "sk-xedoc-YOUR_KEY"
      },
      "models": {
        "gpt-5.6-terra": {
          "name": "GPT-5.6 Terra"
        }
      }
    }
  }
}

Expand the model picker

The minimal example adds one model. Automatic setup fetches the current model catalog and adds the supported models with their protocol and capability settings.

Reference: OpenCode providers.

Keep building

One assistant. All your tools.

Validate your key, choose your clients and let XEDOC make the connection.

Choose the right model.

Canonical IDs, supported protocols and a model picker without duplicate context variants.