Providers

Setting up your First Provider

1. Press Add Entry

2. Select the provider you want to set up

3. Fill out required information

4. Press Submit.

Reconfigure a Provider

You can always change provider settings: Click the three dots → Reconfigure. This will open the set up menu again.

LLM Vision combines multiple AI providers into an easy to use integration. These AI providers are supported:

If you are unsure which model to use, there is a comparison available here: Choosing the right model

Cloud based Providers

Easy to set up and blazingly fast

OpenRouter

Pay as you go

Recommended Models

gpt-5-minigpt-4o-minigemini-2.5-flashgemini-2.5-proclaude-opus-4-1claude-sonnet-4

OpenAI

Pay as you go

Recommended Models

gpt-5-minigpt-4o-minigpt-4o

Anthropic

Pay as you go

Recommended Models

claude-opus-4-1claude-sonnet-4

Google

FreePay as you go

Recommended Models

gemini-2.5-flashgemini-2.5-progemini-2.0-flash

AWS Bedrock

Pay as you go

Recommended Models

Amazon Nova

Azure AI Foundry

Pay as you go

Recommended Models

gpt-5-minigpt-4o-minigpt-4o

Groq

Free

Recommended Models

llama-4-scoutllama-4-maverick

Self-hosted Providers

Achieve maximum privacy by hosting LLMs on a local machine

Ollama

Self-hosted

Recommended Models

gemma3llama3.2-visionminicpm-vllava1.6

Open WebUI

Self-hosted

Recommended Models

gemma3llama3.2-visionminicpm-vllava1.6

LocalAI

Self-hosted

Recommended Models

gemma3llama3.2-visionminicpm-vllava1.6

Setup

Each provider is slightly different but most will require and API key. Self-hosted providers need a base url and port.

Providers can also be reconfigured if you need to change anything later!

To setup your first provider:

1. Navigate to Devices & Services in the Home Assistant settings

2. Add Integration

3. Search for 'LLM Vision'

4. Select the provider you want to set up from the dropdown

5. Enter all required details

On success you will see LLM Vision in your integrations. From here you can set up new providers or delete existing ones.

Using Providers in Actions

You can have multiple different configurations per provider. This is especially useful for local providers, for example when you have two machines hosting different models.

Multiple configurations for Ollama with different hosts

When running an action, you can select one of your provider configurations:

Selecting a provider