SPACE ROUTER · Cherry Studio / Chatbox / LobeHub
Cherry Studio / Chatbox / LobeHub + Space Router
Install one chat client, add Space Router as a custom provider, and verify a conversation.
Before you start
| Field | Value | Check |
|---|---|---|
| Supported setup | Windows; macOS; LobeHub also has a web interface | Choose the matching OS installer; keep your current configuration backup |
| Account | A Space Router account and matching group credit/subscription | The app’s own login and the router API key are separate |
Download stages are shown in the terminal. Direct downloads show a progress bar or received bytes; package managers use their own output. A percentage may be unavailable. Keep the terminal open until the final installation and connection results.
Space Router one-click scripts report INSTALLATION separately from CONNECTION. DONE means the app or command was checked; VERIFIED means the stated response test passed. SKIPPED / NOT CONFIGURED needs the connection steps. FAILED / INCOMPLETE needs the displayed error fixed. A CLI test does not verify a desktop app or editor panel.
Model examples and placeholders must be replaced with IDs allowed by your key’s group. You can install the app first, then create the key before the connection steps.
When this tool uses your Space Router endpoint and key, its model requests use your Space Router balance or eligible subscription. App sign-in, app subscriptions and cloud-only features are separate. Confirm the actual route in usage history after testing.
1 · Install from zero
Choose one chat app
Use the official Cherry Studio, Chatbox or LobeHub website. Choose the Windows or Mac build matching your device; avoid repackaged installers.Install and open it
On Windows run the downloaded installer. On Mac open the downloaded package and place the app in Applications as instructed. Complete any normal app sign-in; that account does not replace your Space Router key. For LobeHub web use, open your own chosen trusted instance.Locate provider settings
Open Settings and find Models, Providers or Language Models. You need a form that accepts your own API key and an API host/base URL. Use the relevant application subsection below, then start a fresh chat.
Do not buy a second app subscription just to obtain a Space Router key. Features, sync and optional hosted services may have the app’s own terms.
2 · Create your API key
Sign in to Space Router
Open space.stationine.com and sign in to your own account. Confirm you have usable credit or an eligible subscription before testing.Create a dedicated API key
Open API Keys → Create API Key. Name the key after this tool. Select GPT / OpenAI for OpenAI-compatible setup; use the groups actually available to your account. A key for a different model family is not interchangeable.Copy the full key and the model ID
Save the full key in your password manager. Copy one exact model ID allowed by that key’s group from Available Channels. Keep any limits or expiry you need. A model shown in an app’s public list may not belong to your key.Keep the key private
Paste the key only into your own app or local credential store. Do not include it in shared screenshots, project files, import links or support messages. For two purchased groups, create two separate keys.

3 · Connect Space Router
| Field | Value | Check |
|---|---|---|
| API format | OpenAI-compatible Chat Completions | The examples here use a GPT-group key |
| Base URL / API host | https://space.stationine.com/v1 | If the app shows a resulting request URL, it should end /v1/chat/completions exactly once |
| Key / model | YOUR_GPT_GROUP_KEY / YOUR_GPT_MODEL_ID | Replace both with your own group values |
Cherry Studio
Add a provider in settings
Open Settings → Model Providers. Add a custom OpenAI-compatible provider named Space Router, then enter the host and key above. Enable the provider.Add and select the model
Open the provider’s model management, fetch models or add the exact ID manually, then save. Start a new assistant/chat and select that model under Space Router.
Chatbox
Choose a custom AI provider
Open Settings → Model/AI Provider. Choose or add a custom OpenAI-compatible provider, then enter API Hosthttps://space.stationine.com/v1, API Path/chat/completions, the key and model. In versions that expose a full endpoint instead of a base host, use https://space.stationine.com/v1/chat/completions.Save and start a new conversation
Save the provider and make it active. Create a new chat and check the provider/model shown for that conversation; existing chats may keep their previous selection.
LobeHub / LobeChat
Choose the trusted instance you use
In your chosen LobeHub/LobeChat instance, open Settings → AI/Language Model Providers and enable OpenAI or a custom OpenAI-compatible provider. The exact label varies by release. Only enter your key into an instance you trust to handle it.Set the proxy/base URL and custom model
Set the API key and custom API/proxy address to the values above. Add the allowed model ID if it is not listed. Save, then choose it in a fresh conversation. Hosted versions without custom-provider fields cannot be configured by changing an unrelated account setting.
In every app, verify the rendered final URL or error details if a duplicate /v1 appears. Field labels differ by app version; do not switch to an official provider endpoint while keeping a Space Router key.
Choose the model for this conversation
Provider settings and the current conversation’s model selection are separate. After saving a provider, start a new task/chat and explicitly select its model. If the app has separate planning, acting or helper models, keep each on an allowed Space Router route before testing.
4 · Verify a real response
Reopen the client
Save your settings, fully quit the app and reopen it. Start a new conversation. Select the Space Router provider and the exact model allowed by your key; do not leave the previous provider selected.Ask a small, checkable question
SendWhat is 17 plus 25? Reply with just the number.Expect a complete reply of42. This uses your account credit at the selected model’s normal rate. A speed check or HTTP 200 alone is not enough.Match the usage record
Open Space Router’s usage history. Match the request time, model and API key with this test. A client reply plus the matching record is stronger evidence than an “installed” or “connected” label.
Troubleshooting
| Symptom | What to check |
|---|---|
| 401 / 403 | Check the full key, its enabled/expiry/IP settings, and group permission. Re-paste privately; do not publish the key. |
| 404 / model not found | Match the API format, base URL and exact model ID. Do not add /v1 twice or enter a full request path into a base-URL field. |
| 429 / credit or quota error | Check account credit, key quota and rate/concurrency limits. Repeated retries do not add balance or remove a limit. |
| Timeout / incomplete reply | Check the network and channel status. Keep the time and request ID for support; do not treat a partially received reply as a successful test. |
| Still uses the previous provider | Reopen the client, start a new conversation, and check its selected provider and any environment/config overrides. Restore a backup instead of deleting the whole configuration. |
| Host contains /v1/v1 | Inspect whether the field expects a base URL or a complete endpoint and correct that field only. |
If you need help, send the app version, operating system, model ID, timestamp and request ID to Space Router support. Redact keys and private project content.
Backup, update and recovery
Before editing an existing setup, copy the chosen app’s provider settings/export to a private backup. Keep the original provider name and model selection so you can return to them. Do not put credential backups in a project repository.
To recover, close the client, restore the specific file or select the previous provider, then reopen it. Keep conversations and other unrelated settings. Revoke an exposed key in Space Router and create a replacement only if it was actually exposed.
Use the application’s normal update flow. Recheck the provider selection and one real response after an update; do not rerun several installers together when one is still active.