# ai&

Source: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible/aiand

[ai&](https://www.aiand.com/inference) is an official Open WebUI partner bringing open-weight AI models to teams in Japan through its own domestic infrastructure. Pair Open WebUI's chat and collaboration features with ai&'s hosted inference to give your team an AI workspace without operating GPU servers.

## Why Choose ai& for Teams in Japan?

- **Run inference close to your users.** ai& processes inference on its own infrastructure in Japan, designed for low latency across the Asia-Pacific region.
- **Keep inference processing in Japan.** ai&'s [service terms](https://www.aiand.com/legal/inference-terms-of-service) provide for domestic processing of inputs and outputs and prohibit using that content to train models.
- **Choose the model that fits the work.** Access model families such as Kimi, DeepSeek, and GLM through one API. Compare models in Open WebUI and choose from the [ai& catalog](https://docs.aiand.com/models/catalog/) for coding, reasoning, and everyday team chat.
- **Start small and grow.** Begin with per-token pricing, then explore reserved compute and custom SLAs as your team's needs expand. See [ai&'s plans and pricing](https://www.aiand.com/inference).

**Ready to bring Japan-hosted AI to your workspace?** [Create an ai& API key](https://console.aiand.com/) and follow the steps below. For a Japanese-language overview, visit [ai& Inference 日本語](https://www.aiand.com/jp/inference).

## Step 1: Get Your API Key

1. Sign in at [console.aiand.com](https://console.aiand.com/).
2. Create an API key and store it securely; the key is shown only once.
3. Add credits to your account to use the API.

See the [ai& quick start](https://docs.aiand.com/getting-started/) for account and billing setup.

## Step 2: Add the Connection in Open WebUI

1. Go to **Settings > Admin > Connections** and find the **Manage OpenAI API Connections** list.
2. Click **Add Connection**.
3. Enter the following settings:

| Setting | Value |
| --- | --- |
| URL | https://api.aiand.com/v1 |
| API Key | Your ai& API key |
| Model IDs | Leave empty to discover available models, or add specific model IDs to limit the list |

1. Leave **Provider** under **Advanced** set to **Default**.
2. Click **Verify Connection**, then **Save**.

ai& exposes a [`/v1/models` endpoint](https://docs.aiand.com/api/models/) for model discovery. Use the exact model IDs returned by that endpoint when adding models to the allowlist.

## Step 3: Start Chatting

Open a new chat, select an ai& model from the model selector, and send a message.

Choose a model with the capabilities your workflow needs. Check the [ai& model catalog](https://docs.aiand.com/models/catalog/) for available models, context windows, and support for features such as reasoning, vision, and tool calling.

For connection troubleshooting and other configuration options, see the [OpenAI-Compatible guide](/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible).