---
title: "Local API quickstart"
description: "Call models hosted by Noema on your Mac from curl, the OpenAI Python SDK or the Anthropic Python SDK."
version: "Noema 4.2+"
platforms: ["Mac"]
reviewed: "2026-10-23"
canonical: "https://noemaai.com/docs/local-api-quickstart"
---

# Local API quickstart

Start the Local API on your Mac, copy its address and key, and send your first request.

Noema for Mac can serve its models over HTTP through OpenAI-compatible and Anthropic-compatible endpoints. Requests run on the Mac; the client does not need the model installed. The [Local API reference](https://noemaai.com/docs/local-api) covers every endpoint, pairing and troubleshooting.

## Start the server

1. On the Mac, open **Developer** in Noema's sidebar and turn on **Run API server**. The header shows the port Noema is listening on (12345 by default).
2. Under **Access**, choose **This Mac** to accept requests only from this Mac, or **Local network** to let other devices on your network connect.
3. If other devices can reach the server, turn on **Require API key**.
4. Copy the address under **Connection**. On the Mac itself it is `http://127.0.0.1:12345/v1`; the **Local network** row shows the address other devices use.
5. Keep Noema running and the Mac awake while clients use it.

![Noema's Developer view on Mac with copyable setup snippets for Claude Code, Codex, curl and Python](https://noemaai.com/image-uploads/noema-42-local-api-1330.webp)

**Local API.** The Clients section on the Developer page has ready-made setup snippets for Claude Code, Codex, curl and Python. Snippets read the key from NOEMA_API_KEY, so they never contain it. Shown in Noema 4.2.

## Set the address and key

The samples read the server address and key from environment variables. Use the address from **Connection** without the trailing `/v1`. With **Require API key** off, the server does not check a key; Noema's own Claude Code snippet passes the placeholder `local` for clients that insist on one.

```bash
# The address from Developer → Connection, without /v1.
export NOEMA_BASE_URL="http://127.0.0.1:12345"
# The key, if Require API key is on.
export NOEMA_API_KEY="<your key>"
```

## List the models

`/v1/models` returns the models the server exposes. Use one of the returned identifiers in every request. The Developer page also shows each model's ID with a copy button.

```bash
curl "$NOEMA_BASE_URL/v1/models" \
  -H "Authorization: Bearer $NOEMA_API_KEY"

# Use one of the returned ids for the requests below.
export NOEMA_MODEL="<model id>"
```

## Send a chat completion

`/v1/chat/completions` accepts the OpenAI Chat Completions request format.

```bash
curl "$NOEMA_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $NOEMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<EOF
{
  "model": "$NOEMA_MODEL",
  "messages": [
    {"role": "user", "content": "Explain a context window in two sentences."}
  ]
}
EOF
```

## Use an SDK

Point an official SDK at the Mac. The OpenAI SDK's `base_url` includes `/v1`; the Anthropic SDK adds `/v1/messages` itself, so its `base_url` is the bare address. Install them with `pip install openai anthropic`.

**OpenAI Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url=f"{os.environ['NOEMA_BASE_URL']}/v1",
    api_key=os.environ["NOEMA_API_KEY"],
)

response = client.chat.completions.create(
    model=os.environ["NOEMA_MODEL"],
    messages=[{"role": "user", "content": "Explain a context window in two sentences."}],
)
print(response.choices[0].message.content)
```

**Anthropic Python**

```python
import os
import anthropic

client = anthropic.Anthropic(
    base_url=os.environ["NOEMA_BASE_URL"],
    api_key=os.environ["NOEMA_API_KEY"],
)

message = client.messages.create(
    model=os.environ["NOEMA_MODEL"],
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain a context window in two sentences."}],
)
print("".join(block.text for block in message.content if block.type == "text"))
```

The OpenAI example calls `/v1/chat/completions`; the Anthropic example calls `/v1/messages`.

## Authentication

Each client sends the key its own way by default: curl in these samples and the OpenAI SDK as an `Authorization: Bearer` header, the Anthropic SDK as an `x-api-key` header. Use the credential exactly as Noema's Local API settings present it.

For an authentication error, check the selected credential and the paired device. Revoke access under **Authorized devices** for a client you no longer use.

## Other endpoints

`/v1/responses` accepts the Responses request format, and `/v1/messages/count_tokens` returns a token-count estimate for Messages clients.

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

## Call the server from another device

Enable local-network serving and pair the device with the QR flow, or configure the displayed credentials. If the client reaches the Mac by a custom DNS name, add that name to **Trusted hosts**.

The listener can use HTTP on a trusted local network. Do not assume Constellation's encryption applies to this separate API; keep it on a network you control.

## Related documentation
- [Local API reference](https://noemaai.com/docs/local-api)
- [MCP connectors](https://noemaai.com/docs/connectors)
- [Remote endpoints](https://noemaai.com/docs/remote-endpoints)
- [Run Noema models](https://noemaai.com/docs/run-noema-models)