# Connect LM Studio

> LM Studio serves only the model you have loaded, not every model you downloaded - so load one, start the server, enable CORS, and give Big-AGI the address.

- Canonical: https://big-agi.com/docs/connect-lmstudio
- Minimum tier: open  [Open ⊂ Free ⊂ Pro - a tier only ever ADDS to the Open baseline]
- Kind: provider · Last content update generation: 2026-07-27 · Review by: 2026-10-27
- Answers: How do I start the LM Studio server? · What address do I enter in Big-AGI? · Why does it list a model that never answers?

LM Studio serves the model currently loaded in the app, so a model you downloaded but never loaded is visible to you and unreachable to Big-AGI. The connection is an address, with no key involved, and the hosted app uses it exactly as a self-hosted one does ([models on your own machine](/docs/connect-models#models-on-your-own-machines)).

## Loaded, not just downloaded

Install the app from [lmstudio.ai](https://lmstudio.ai/), download one model, and load it. Only the loaded one is served. Weights are large and speed follows your memory and GPU, so start small.

## Starting the server and enabling CORS

1. Run `lms server start`, or open the app's **Developer** tab and switch **Status** from `Stopped` to `Running` ([LM Studio's own instructions](https://lmstudio.ai/docs/app/api/headless)).
2. It listens on port `1234`, making the base address `http://localhost:1234`. Opening `http://127.0.0.1:1234/v1/models` in a browser tab shows what it is serving, independently of Big-AGI.
3. Turn on **Enable CORS** under **Developer** -> **Settings**. Without it the server takes only same-origin requests and refuses your browser ([server settings](https://lmstudio.ai/docs/developer/core/server/settings)).

## The address, prefilled

Open **Models** with `Ctrl + Shift + M`, press **More Services** if the **Setup AI Models** wizard shows, then **Add** -> **LM Studio**. Check **LM Studio API**, which arrives prefilled with `http://localhost:1234`, and press **Models** ([add and manage your keys](/docs/connect-models)).

## Direct Connection

Always eligible, and the mode this runtime's own help text is written for: *"Connect directly to LM Studio from your browser. Requires CORS to be enabled in LM Studio."* With it off, the fetch comes from the Big-AGI fast edge servers, which cannot see your `localhost`.

> **Direct Connection works only with your API key stored in the browser**, and with an AI service that permits direct browser calls (CORS). Where it cannot be used, requests route through the Big-AGI fast edge servers instead - everything still works, within the standard upload size and time limits.

## When this doesn't work

| What you see | What it means | What to do |
|---|---|---|
| `[LM Studio network issue]: Could not connect:` | The server is stopped, or the address is wrong. | [I don't see the model I want](/docs/issue-messages) |
| It answers in the terminal and not in Big-AGI | CORS is off, so the server refuses your browser's origin. | Enable it: [my local models don't show up](/docs/issue-messages) |

## Related

- [Models on your own machine](/docs/connect-models#models-on-your-own-machines)
- [What leaves your browser](/docs/privacy-data-flow)
- [I don't see the model I want](/docs/issue-messages)