LobeHub
LobeHub

Using Unsloth in LobeHub

Unsloth runs local models and exposes an OpenAI-compatible API through Unsloth Studio. LobeHub connects to your running instance; this integration does not provide a hosted inference account or download models for you. Check the model's license and your hardware requirements before downloading it.

Step 1: Start Unsloth Studio

  • Follow the official installation guide to install Unsloth Studio and start its desktop app or CLI service.
  • Download a model in Studio and make it available for inference. The Unsloth model catalog lists available models; a catalog entry does not mean the model is installed locally.
  • The default API base URL is http://127.0.0.1:8888/v1. If you explicitly start Studio on another port, replace 8888 with that port, such as 8000. Use the base URL ending in /v1, not the full /chat/completions path.

Step 2: Choose How LobeHub Connects

  • Server requests require the LobeHub server to reach Studio. 127.0.0.1 refers to the server itself; inside Docker it refers to the container. Use an address reachable from that server or container when Studio runs elsewhere.
  • Client Request Mode sends requests from your browser. Studio must allow the LobeHub page's origin through CORS, and requests from another browser origin require a real API key from your Studio instance. A successful keyless terminal request does not establish browser access. Do not use a made-up key.

Step 3: Configure and Check the Connection

  • Open App Settings → AI Providers
  • Find and select the Unsloth provider from the list
  • Enable the provider, enter your API base URL, and enter the real Studio API key when authentication is required. Enable Client Request Mode only for a browser-accessible endpoint.
  • Click Fetch Model List and choose a model returned by your running Studio instance. If adding a model manually, use its exact local API model ID. The two built-in example models are not enabled by default and are not guaranteed to be installed. Existing saved model selections are preserved.
  • Load the model in Studio, then fetch the list again to discover its tool and vision capabilities. Studio reports these capabilities for the loaded model; they may be unavailable for models that are not loaded.
  • Select that model for Connection Check and run the check. After it succeeds, select the same model for your assistant.

Connection Problems

  • CORS or failed preflight: As of September 6, 2026, Studio desktop API-only mode rejects browser origins on other local ports. The upstream fix, unsloth#10084, is still open. Enabling Client Request Mode alone does not fix this. Use a Studio mode that allows your origin, or a server request from a host that can reach Studio.
  • Not authenticated / Invalid token payload: Cross-origin browser calls need valid Studio authentication even when a keyless terminal call works. Enter a real key; an arbitrary placeholder will be rejected.
  • Connection refused or unknown model: Check the actual listening port, server/container reachability, and the model list returned by this Studio instance. Fetching the list does not itself prove that model inference succeeds.

For shared server configuration, see the Unsloth environment variables. Local inference uses your own hardware; this provider does not define a per-token hosted API price. Refer to Unsloth's official site for current product availability and commercial offerings.