# 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 {% hint style="success" %} **You can always change provider settings**: Click the three dots → Reconfigure. This will open the set up menu again. {% endhint %}
LLM Vision combines multiple AI providers into an easy to use integration. These AI providers are supported: {% hint style="info" %} If you are unsure which model to use, there is a comparison available here: [Choosing the right model](https://llmvision.gitbook.io/getting-started/choosing-the-right-model) {% endhint %} ## Cloud based Providers Easy to set up and blazingly fast
OpenRouterPay as you goRecommended Modelsgpt-5-mini, gpt-4o-mini, gemini-2.5-flash, gemini-2.5-pro, claude-opus-4-1, claude-sonnet-4
OpenAIPay as you goRecommended Modelsgpt-5-mini, gpt-4o-mini, gpt-4o
AnthropicPay as you goRecommended Modelsclaude-opus-4-1, claude-sonnet-4
GoogleFree, Pay as you goRecommended Modelsgemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash
AWS BedrockPay as you goRecommended ModelsAmazon Nova
Azure AI FoundryPay as you goRecommended Modelsgpt-5-mini, gpt-4o-mini, gpt-4o
GroqFreeRecommended Modelsllama-4-scout, llama-4-maverick
## Self-hosted Providers Achieve maximum privacy by hosting LLMs on a local machine
OllamaSelf-hostedRecommended Modelsgemma3, llama3.2-vision, minicpm-v, llava1.6Broken file
Open WebUISelf-hostedRecommended Modelsgemma3, llama3.2-vision, minicpm-v, llava1.6
LocalAISelf-hostedRecommended Modelsgemma3, llama3.2-vision, minicpm-v, llava1.6
## Setup {% hint style="info" %} Each provider is slightly different but most will require and API key. Self-hosted providers need a base url and port. {% endhint %} {% hint style="success" %} Providers can also be reconfigured if you need to change anything later! {% endhint %} **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 {% hint style="info" %} 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. {% endhint %}

Multiple configurations for Ollama with different hosts

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

Selecting a provider