OpenCode Desktop Integration

Connect OpenCode Desktop to 200+ models through PassingRight. No config files — just open Settings, connect, and start building.

OpenCode Desktop is the GUI desktop app version of OpenCode — an open-source AI coding agent with a full visual interface for managing providers, models, and sessions. PassingRight is a built-in provider, so setup takes under a minute with no config files required.

Looking for the CLI version? See the OpenCode CLI guide.

Two Built-In Providers

OpenCode ships two PassingRight entries, sharing one endpoint and one API key. PassingRight lists provider-pinned models (anthropic/claude-opus-5, named "Claude Opus 5 (Anthropic)") for pay-as-you-go keys; DevPass (PassingRight) lists canonical models (claude-opus-5) that the gateway routes for you. See the CLI guide for the full comparison.

Using DevPass? Connect DevPass (PassingRight). Provider-pinned routing is not available on coding plans, so canonical model IDs are the ones that work.

Prerequisites

OpenCode Desktop installed — download for Windows or macOS
An PassingRight API key — sign up free (no credit card required)

Installation

Download OpenCode Desktop from opencode.ai/download and install it for your platform:

macOS (Apple Silicon) — .dmg installer
macOS (Intel) — .dmg installer
Windows — .exe installer

You can also install on macOS via Homebrew:

brew install --cask opencode-desktop

Setup

Open Providers Settings

Launch OpenCode Desktop. Click the Providers section in the left sidebar under Server. You'll see the list of built-in providers:

OpenCode Desktop Providers screen

Find PassingRight

Click Show more providers at the bottom of the list, or click + Connect on any entry to open the provider search. Type LLM in the search box — both PassingRight and DevPass (PassingRight) appear under "Other":

Select the one matching your key. You can connect both — they take the same key, and each contributes its models to the picker.

Enter Your API Key

OpenCode will show the Connect PassingRight dialog. Paste your PassingRight API key (starts with llmgtwy_) and click Continue:

Connect PassingRight — enter API key

Select a Model

Once connected, open the model picker from the chat input bar. Type llm to filter PassingRight models. Pinned entries carry their serving provider in the name — "Claude Opus 5 (Anthropic)", "GPT-5.5 (Azure)" — while DevPass entries show the canonical name:

PassingRight model selection

Start Building

Select a model and start chatting. All requests route through PassingRight — you'll see usage, costs, and logs in your dashboard:

OpenCode Desktop chat active with PassingRight

Why Use PassingRight with OpenCode Desktop

200+ models — Claude, GPT, Gemini, Llama, DeepSeek, and more from 40+ providers
One API key — Stop managing separate keys for each provider
Cost tracking — See exactly what each session costs in your dashboard
Response caching — Repeated requests hit cache automatically
Automatic fallback — If a provider is down, requests route to an alternative
Volume discounts — Check discounted models for savings up to 90%

Switching Models

You can switch models at any time from the model picker in the chat input bar. Click the current model name, type llm to filter to PassingRight models, and select a new one. The switch takes effect immediately for the next message.

Locking to a Specific Provider

Pick a model from the PassingRight entry to choose its upstream provider. PassingRight still fails over to an alternative provider if that one is down; to make the pin strict, pass the X-No-Fallback header via a custom opencode.json in your project root:

{
	"provider": {
		"llmgateway-providers": {
			"options": {
				"headers": {
					"X-No-Fallback": "true"
				}
			}
		}
	}
}

Disabling fallback means requests will fail if the chosen provider is down. See the routing docs for details.

Need help? Join our Discord community for support and troubleshooting assistance.