> For the complete documentation index, see [llms.txt](https://docs.diaflow.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.diaflow.io/workflow-builder/nodes/public-ai-llm-models.md).

# Public AI/LLM Models

Public AI models let you use Diaflow with your own provider account, you connect your own API key, then select the model you want in a workflow. This setup is often called **BYOK** — Bring Your Own Key.

<figure><img src="/files/MUZ4r2lx1hbJT4lOUQjA" alt=""><figcaption></figcaption></figure>

## Why use public models

Use public models when you want more control over:

* **Model choice:** Pick the provider that matches your use case.
* **Cost:** Pay your AI provider directly based on your usage.
* **Flexibility:** Switch providers as your needs change.

{% hint style="info" %}
Diaflow runs the workflow. Your AI provider bills the model usage.
{% endhint %}

## What you need before you start

To use a public model, make sure you have:

* An active account with the AI provider.
* A valid API key from that provider.
* The right budget and permissions on that account.

## Available providers

Choose a provider below to see supported models and setup details:

* [OpenAI Cloud](/workflow-builder/nodes/public-ai-llm-models/openai-cloud.md)
* [Perplexity Cloud](/workflow-builder/nodes/public-ai-llm-models/perplexity-cloud.md)
* [BytePlus Cloud](/workflow-builder/nodes/public-ai-llm-models/byteplus-cloud.md)
* [Deepseek Cloud](/workflow-builder/nodes/public-ai-llm-models/deepseek-cloud.md)
* [Anthropic Cloud](/workflow-builder/nodes/public-ai-llm-models/anthropic-cloud.md)
* [Replicate](/workflow-builder/nodes/public-ai-llm-models/replicate.md)
* [Straico](/workflow-builder/nodes/public-ai-llm-models/straico.md)
* [OpenRouter](/workflow-builder/nodes/public-ai-llm-models/openrouter.md)
* [Cohere Cloud](/workflow-builder/nodes/public-ai-llm-models/cohere-cloud.md)
* [Google Gemini Cloud](/workflow-builder/nodes/public-ai-llm-models/google-gemini-cloud.md)
* [MistralAI Cloud](/workflow-builder/nodes/public-ai-llm-models/mistralai-cloud.md)
* [ElevenLabs Cloud](/workflow-builder/nodes/public-ai-llm-models/elevenlabs-cloud.md)
* [Azure Cloud](/workflow-builder/nodes/public-ai-llm-models/azure-cloud.md)
* [AWS Bedrock Cloud](/workflow-builder/nodes/public-ai-llm-models/aws-bedrock-cloud.md)

## How it works in Diaflow

In most cases, the process is simple:

1. Add the model node to your workflow.
2. Connect your provider API key.
3. Choose the model and run your task.

This gives your team access to external AI models without leaving Diaflow.

## When to choose public models

Public models are a good fit when your business needs:

* Access to a specific provider or model family.
* Direct control over provider-level pricing.
* A fast way to test different model vendors.

<figure><img src="/files/0Vf5goI9egwvntx7OkLS" alt=""><figcaption></figcaption></figure>

If you prefer models managed inside Diaflow, use [Private AI/LLM Models](/workflow-builder/nodes/private-ai-llm-models.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://docs.diaflow.io/workflow-builder/nodes/public-ai-llm-models.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.