Installations

Install SuperCodex with one copied command.

The product path is command-first: the dashboard copies the exact macOS or Windows installer command for the signed-in user. Direct package downloads and manual provider fields stay as fallback details.

Open dashboard installer

SuperCodex is the first-class installer path

Users should not download random files or edit JSON by hand. They copy the OS-specific command from Luma Cloud App and paste it into Terminal or PowerShell.

macOS Apple Silicon

1Open Luma Cloud dashboard and go to SuperCodex or Install.
2Click Copy install command on macOS Apple Silicon.
3Open Terminal, paste the copied command, and press Return.
4Wait for SuperCodex to start and show the Luma Cloud quota indicator.

macOS Intel

1Open Luma Cloud dashboard and go to SuperCodex or Install.
2Click Copy install command on macOS Intel.
3Open Terminal, paste the copied command, and press Return.
4Wait for SuperCodex to start and show the Luma Cloud quota indicator.

Windows

1Open Luma Cloud dashboard and go to SuperCodex or Install.
2Click Copy install command on Windows.
3Open PowerShell, paste the copied command, and press Enter.
4Keep PowerShell open if it reports an error; it prints the installer log path for support.

Exact provider values

These are the fallback fields for any OpenAI-compatible IDE form.

Provider ID

luma-cloud

Display name

Luma Cloud

Provider type

OpenAI-compatible

Base URL

https://api.lumaos.cloud/v1

Default model

gpt-5.5-xhigh

Supported models

gpt-5.5, gpt-5.5-xhigh, gpt-5.5-high, gpt-5.5-medium, gpt-5.5-low

Output limit

1024

OpenCode timeout

600000

OpenCode chunkTimeout

300000

Client matrix

One provider contract for every coding surface.

Each client gets the smallest correct setup path. Installer where we can control the local profile; provider fields where the client only exposes an OpenAI-compatible form.

Guide

OpenCode

Copy installer from dashboard

Best path for normal users. The soft installer backs up existing config and merges only provider.luma-cloud, endpoint, key, models, and safe limits.

Open guide

Dashboard installer

SuperCodex

One copied command per OS

Install with the copied macOS or Windows command from the dashboard. The step-by-step flow is at the top of this page; the dashboard copies the exact command for your account.

Open guide

Guide

OpenClaw

Use the OpenClaw guide

OpenClaw uses the public Luma Cloud endpoint plus the workspace starter key and canonical model id.

Open guide

Manual setup

Cursor

Custom OpenAI provider

Use the base URL, bearer key, and any supported model id from this page. Keep model ids lowercase, for example gpt-5.5-xhigh.

Open guide

Manual setup

Continue / VS Code

OpenAI-compatible model block

Set apiBase or baseURL to the Luma Cloud /v1 endpoint and use the same workspace key. The supported model list is generated from the shared catalog.

Open guide

Manual setup

Cline

OpenAI-compatible API provider

Use the /v1 endpoint from your dashboard and the starter key. Do not paste localhost or other internal URLs.

Open guide

Manual setup

Roo Code

OpenAI-compatible API provider

Use the same endpoint, key, and model ids as Cline. Verify native tool-call streaming before claiming full tool support.

Open guide

Manual setup

Zed

OpenAI-compatible settings

Add the Luma Cloud api_url and available model ids to the Zed assistant/provider settings.

Open guide

Provider UX

Why OpenRouter is one step, and how Luma Cloud gets there.

The goal is the same: provider id, endpoint, key, model. Manual OpenAI-compatible setup works now; native catalog listing is a separate provider-adoption track.

Why OpenRouter feels automatic

OpenRouter is already listed in OpenCode's provider flow, and many OpenRouter models are preloaded by OpenCode. The user adds a key; OpenCode already knows the provider and model catalog.

What custom providers require today

OpenCode's Other provider path stores a credential first, then expects provider metadata and models from config. That is why the model list has to arrive from a profile or remote config.

What Luma Cloud now exposes

The public API serves /v1/models for SDKs and /.well-known/opencode for OpenCode remote defaults. The installer is now only the compatibility fallback for current custom-provider builds.

Fallback

Manual setup stays short when a client has only a form.

Use this block for Cursor, Continue, VS Code extensions, local SDK tests, and any client that asks for an OpenAI-compatible provider.

Copy-safe manual block

Always use the /v1 endpoint from your dashboard. Never paste localhost or other internal URLs into client settings.

Provider ID: luma-cloud
Display name: Luma Cloud
Provider type: OpenAI-compatible
Base URL: https://api.lumaos.cloud/v1
API key: starter key from Luma Cloud App -> API
Model: gpt-5.5-xhigh
Models: gpt-5.5, gpt-5.5-xhigh, gpt-5.5-high, gpt-5.5-medium, gpt-5.5-low
OpenCode timeout: 600000
OpenCode chunkTimeout: 300000

What the installer writes

The local file stays on the user's machine and is merged with existing plain JSON config.

provider.luma-cloud with @ai-sdk/openai-compatible

baseURL set to https://api.lumaos.cloud/v1

starter key from the signed-in workspace

all currently allowed model ids

limit.output set to 1024 to match the current output limit

default model luma-cloud/gpt-5.5-xhigh

Other clients

No dedicated guide? Manual setup still works.

Any tool with an OpenAI-compatible provider form can connect today with the base URL, key, and model values from this page. The full universal path lives in the API setup guide.

JetBrains AI Assistant

Manual setup

Windsurf

Manual setup

AnythingLLM

Manual setup

LangChain / OpenAI SDKs

Manual setup

Troubleshooting

When the provider form still fails.

These checks separate bad local setup from a real backend issue.

Request body mismatch

Re-run the installer. Old OpenCode profiles often advertise output 128000 or omit timeout/chunkTimeout, which makes clients send or abort requests outside the current request limits.

401 or invalid key

Copy the starter key again from the signed-in dashboard. Do not use the endpoint as the key.

Models not visible

Restart OpenCode after installing. If needed, choose luma-cloud/gpt-5.5-xhigh manually.

OpenCode opens empty after a failed install

Rename ~/.config/opencode/opencode.json to opencode.broken-lumacloud.json, restart OpenCode, then run the current soft installer from the dashboard.

Quota exhausted

The provider is connected. Open Billing or Analytics to inspect the account limit.

Wrong endpoint

Use the base URL ending in /v1. Do not append /chat/completions in provider settings.

Wrong model label

Use gpt-5.5-xhigh. Marketing labels like GPT-5.5X High are not the copy-safe field value.

Backend contract

All public clients should enter through https://api.lumaos.cloud/v1.

OpenCode details API setup Provider adoption