---
title: "Local API Server"
description: "Serve Noema models to compatible clients through Chat Completions, Responses, and Messages endpoints, with pairing and request controls."
version: "Noema 4.2+"
platforms: ["Mac"]
reviewed: "October 17, 2026"
canonical: "https://noemaai.com/docs/local-api"
---

# Local API Server

Let compatible apps and coding clients call models hosted by Noema on your Mac.

## Start the server

1. On the Mac, open the Local API server or Developer page and choose the models to serve.
2. Start the listener and copy the address, model identifier, and authentication details shown by Noema.
3. For another device, enable local-network serving and pair it with the provided QR flow or configure the displayed credentials.
4. Keep Noema running and the Mac awake while a client is using it.

> Serving a local model does not install that model in the client. Its requests are processed on the Noema host.

## Supported endpoint families

| Endpoint | Use |
| --- | --- |
| /v1/models | Discover models exposed by the server. |
| /v1/chat/completions | OpenAI-compatible chat clients. |
| /v1/responses | Clients using the Responses request format. |
| /v1/messages | Clients using the Anthropic Messages request format. |
| /v1/messages/count_tokens | A token-count estimate for Messages clients. |

> Protocol compatibility depends on the endpoint and model. Tool calling, image input, context length, and generation behavior remain limited by the selected model; an endpoint name does not imply support for every hosted-provider feature.

## Pairing, trusted hosts, and request log

- Use authentication and the Authorized devices controls to manage paired clients. Revoke access for a device you no longer use.
- Add a custom DNS hostname to Trusted hosts when needed. The server rejects untrusted Host names; enter the hostname it actually receives.
- Use the request log to inspect incoming requests, model selection, and errors. Logging can be controlled in server settings.
- Keep the listener on a network you control. Off-Grid and server availability controls still apply.

## Troubleshooting

For authentication errors, check the selected credential and paired device. For an unknown model, copy an identifier returned by /v1/models. For a rejected host, check the hostname and Trusted hosts setting.

If a client cannot connect, check that the server is running, the Mac is awake, the port and local-network settings match, and both devices can reach the selected address. A model loading or memory error requires fixing the host model setup.

## Related documentation
- [Running Models Locally](https://noemaai.com/docs/running-llms)
- [Remote Endpoints](https://noemaai.com/docs/remote-endpoints)
- [Privacy & Network Activity](https://noemaai.com/docs/privacy-and-network-activity)