# Connecting to SiliconFlow

SiliconFlow leverages its proprietary inference engine to deliver efficient acceleration for large language model inference. It provides high-performance, cost-effective API services for a wide range of large models with pay-as-you-go pricing, making application development a breeze.

## Configuring the Chat Model

Navigate to the SiliconFlow [API Keys](https://cloud.siliconflow.cn/me/account/ak) page and create a new API Key. Save it for later use.

Visit the SiliconFlow [Models page](https://cloud.siliconflow.cn/me/models) to select your desired model. Note down the model name for later use.

Open the AstrBot WebUI, click `Service Providers` in the left sidebar -> `Add Provider` -> select `SiliconFlow`.

Paste the `API Key` and `Model Name` you obtained earlier, then click Save to complete the setup. You can click the `Refresh` button under `Service Provider Availability` to verify whether the configuration is successful.

![Configuring Chat Model](https://files.astrbot.app/docs/source/images/siliconflow/image.png)