# 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>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://llmvision.gitbook.io/getting-started/setup/providers/cloud-providers.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.