# Cloud Providers

## OpenAI <a href="#openai" id="openai"></a>

Obtain an API key from [OpenAI](https://platform.openai.com/api-keys) and enter it during setup. You will need to add credits to you account before making requests.

{% hint style="info" %}
A pricing calculator is available here: [https://openai.com/api/pricing](https://openai.com/api/pricing/)
{% endhint %}

<details>

<summary>Recommended Models</summary>

**`gpt-5`** Most intelligent and flexible GPT model

**`gpt-5-mini`** Fast, affordable small model

See [OpenAI API docs](https://platform.openai.com/docs/models) for all models.

</details>

## Anthropic <a href="#anthropic" id="anthropic"></a>

Obtain an API key from [Anthropic](https://claude.ai/) and enter it during setup. You will need to add credits to you account before making requests.

{% hint style="info" %}
Pricing is available here: <https://docs.anthropic.com/en/docs/build-with-claude/vision#calculate-image-costs>​
{% endhint %}

<details>

<summary>Recommended Models</summary>

`claude-opus-4-0` Most powerful and capable

`claude-sonnet-4-0` High-performance with exceptional reasoning

See [Anthropic API docs](https://docs.anthropic.com/en/docs/about-claude/models) for all models.

</details>

## Google <a href="#google" id="google"></a>

To use Google Gemini you need to have a Google account and obtain an API key from the [AI Studio](https://aistudio.google.com/app/apikey). Depending on your region, you may need to enable billing.&#x20;

{% hint style="info" %}
Pricing is available here: <https://ai.google.dev/pricing>​
{% endhint %}

<details>

<summary>Recommended Models</summary>

`gemini-2.5-pro` Powerful thinking model for maximum accuracy

**`gemini-2.5-flash`** Fast and affordable all-rounder model

See [Google API docs](https://ai.google.dev/gemini-api/docs/models/gemini) for all models.

</details>

## OpenRouter

Obtain an API key from OpenRouter and enter it during setup. You will need to set up billing for you account before making requests.

{% hint style="info" %}
Pricing is available here: <https://openrouter.ai/models?o=pricing-high-to-low>
{% endhint %}

<details>

<summary>Recommended Models</summary>

See this website to find and compare models: <https://openrouter.ai/models?fmt=cards&input_modalities=image>

</details>

## AWS Bedrock

To deploy a model on AWS, your first must request access to models: <https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/modelaccess>.

Once you have access, create an access key here: <https://us-east-1.console.aws.amazon.com/iam/home?region=us-east-1#/security_credentials>

To use this deployment with LLM Vision you will need:

* Region String
* Access Key
* Secret

Enter these during setup.

## Azure AI Foundry

To deploy a model on Azure AI Foundry follow this guide: <https://ai.azure.com/doc/azure/ai-foundry/how-to/create-projects?tid=b7091c05-52c5-48a7-a4ef-67c41f1cf3a2#prerequisites>

To use this deployment with LLM Vision you will need:

* API key
* Azure OpenAI Endpoint (e.g. `https://llmvision.openai.azure.com/)`
* Deployment name (e.g. `gpt-4o-mini`)

Enter these during setup.

<details>

<summary>Recommended Models</summary>

`gpt-4o` Intelligent and flexible GPT model

`gpt-4o-mini` Fast, affordable small model

See the [model catalog](https://platform.openai.com/docs/models) for all models.

</details>

## Groq

Obtain an API key from [Groq ](https://console.groq.com/keys)and enter it during setup to get started with Groq.

{% hint style="info" %}
Groq is free to use but limits apply. You can check them here: <https://console.groq.com/settings/limits>

Note: Groq does not support `video` and `stream` analyzers.
{% endhint %}

<details>

<summary>Recommended Models</summary>

`meta-llama/llama-4-maverick-17b-128e-instruct` Most accurate

`meta-llama/llama-4-scout-17b-16e-instruct` Fast

See [Groq API docs](https://console.groq.com/docs/vision#supported-model) for all models.

</details>