Anthropic
The Anthropic integrationsIntegrations connect and integrate Home Assistant with your devices, services, and more. [Learn more] adds a conversation agent powered by Anthropic, such as Claude 3.5 Sonnet, in Home Assistant.
Controlling Home Assistant is done by providing the AI access to the Assist API of Home Assistant. You can control what devices and entities it can access from the exposed entities page. The AI can provide you information about your devices and control them.
Legal note: Individuals and hobbyists are welcome to use the Anthropic API for personal use, however, please note that the use of the API is subject to their Commercial Terms of Service, regardless of whether you are an individual or representing a company.
Prerequisites
- This integration requires an API key to use, which you can generate here..
- This is a paid service, we advise you to monitor your costs in the Anthropic portal closely.
Generating an API Key
The Anthropic API key is used to authenticate requests to the Anthropic API. To generate an API key, take the following steps:
- Log in to the Anthropic portal or sign up for an account.
- Enable billing with a valid credit card on the plans page.
- Visit the API Keys page to retrieve the API key you’ll use to configure the integration.
Configuration
To add the Anthropic service to your Home Assistant instance, use this My button:
If the above My button doesn’t work, you can also perform the following steps manually:
-
Browse to your Home Assistant instance.
-
In the bottom right corner, select the
Add Integration button. -
From the list, select Anthropic.
-
Follow the instructions on screen to complete the setup.
Options
To define options for Anthropic, follow these steps:
-
In Home Assistant, go to Settings > Devices & services.
-
If multiple instances of Anthropic are configured, choose the instance you want to configure.
-
On the card, select the cogwheel
. - If the card does not have a cogwheel, the integration does not support options for this device.
-
Edit the options, then select Submit to save the changes.
The integration provides the following types of subentries:
Instructions for the AI on how it should respond to your requests. It is written using Home Assistant Templating.
If the model is allowed to interact with Home Assistant. It can only control or provide information about entities that are exposed to it.
If you choose not to use the recommended settings, you can configure the following options:
The model that will complete your prompt. See models for additional details and options.
The maximum number of tokens to generate before stopping. Note that our models may stop before reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Different models have different maximum values for this parameter. See models for details.
Amount of randomness injected into the response. Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks. Note that even with temperature of 0.0, the results will not be fully deterministic. This parameter is ignored if extended thinking is enabled (see below).
For models with extending thinking support, such as Claude 3.7 Sonnet, this parameter determines the maximum number of tokens Claude is allowed use for its internal reasoning process. Larger budgets can improve response quality by enabling more thorough analysis for complex problems, although Claude may not use the entire budget allocated, especially at ranges above 32K. Anthropic suggests starting at the minimum and increasing the thinking budget incrementally to find the optimal range for Claude to perform well for your use case. Higher token counts may allow you to achieve more comprehensive and nuanced reasoning, but there may also be diminishing returns depending on the task. Be prepared for potentially longer response times due to the additional processing required for the reasoning process. The value must always be less than the Maximum Tokens specified. If the value is below 1024, then extended thinking is disabled. This parameter is ignored if the model does not support extended thinking.
Newer models (starting from Claude 4.6) use the effort parameter, instead of the thinking budget, to control how many tokens Claude uses when responding, trading off between response thoroughness and token efficiency.
Enable the server-side Code execution tool. With this tool, the model can analyze data, perform complex calculations, run system commands, including writing code, in a secure, sandboxed environment.
Enable the server-side Web search tool for direct access to real-time web content, allowing it to answer questions with up-to-date information beyond its knowledge cutoff. Please note that this tool has its own pricing.
Limits the number of web searches that can be performed per user request. Once the limit is reached, no additional searches will be executed during that conversation.
Use cases
The integration provides conversation and ai_task entities powered by Anthropic API. Please refer to the corresponding integrations for more details and examples:
Known limitations
This integration does not integrate with sentence triggers.
Removing the integration
This integration follows standard integration removal. No extra steps are required.
To remove an integration instance from Home Assistant
- Go to Settings > Devices & services and select the integration card.
- From the list of devices, select the integration instance you want to remove.
- Next to the entry, select the three dots
menu. Then, select Delete.