> For the complete documentation index, see [llms.txt](https://docs.flowiseai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/chat-models/azure-chatopenai.md).

# ChatOpenAI

## Prerequisitos

1. Una cuenta de [OpenAI](https://openai.com/)
2. Crear una [API key](https://platform.openai.com/api-keys)

## Configuración

1. **Chat Models** > arrastra el nodo **ChatOpenAI**

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-2627f3a53fb552f36647956265537d09ec5a7a15%2Fimage%20(10)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt="" width="563"><figcaption></figcaption></figure>

2. **Connect Credential** > haz clic en **Create New**

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-9ad11174cc567daff947211332da5ffcca596e08%2Fimage_openAI%20(1).png?alt=media" alt="" width="278"><figcaption></figcaption></figure>

3. Completa la credencial de **ChatOpenAI**

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-66551af4421577a34ef39f8ebbf200bcd74bcb5d%2Fimage%20(2)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt="" width="563"><figcaption></figcaption></figure>

4. ¡Voilà [🎉](https://emojipedia.org/party-popper/), ahora puedes usar el **nodo ChatOpenAI** en Flowise

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-95fc122a3d8752f66a9856f86a7a516615854372%2Fimage%20(3)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt=""><figcaption></figcaption></figure>

## URL base y encabezados personalizados

Flowise admite el uso de URL base y encabezados personalizados para Chat OpenAI. Los usuarios pueden usar fácilmente integraciones como OpenRouter, TogetherAI y otros que sean compatibles con la API de OpenAI.

### TogetherAI

1. Consulta la [documentación oficial](https://docs.together.ai/docs/openai-api-compatibility#nodejs) de TogetherAI
2. Crea una nueva credencial con la API key de TogetherAI
3. Haz clic en **Additional Parameters** en el nodo ChatOpenAI
4. Cambia el Base Path:

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-ba25dada7e958ff10b32ee5f4bdb7c1552cb970f%2Fimage%20(4)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt="" width="563"><figcaption></figcaption></figure>

### Open Router

1. Consulta la [documentación oficial](https://openrouter.ai/docs#quick-start) de OpenRouter
2. Crea una nueva credencial con la API key de OpenRouter
3. Haz clic en Additional Parameters en el nodo ChatOpenAI
4. Cambia el Base Path y Base Options:

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-6798fc57a237cb6878be564d89f211906db7a471%2Fimage%20(5)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt="" width="563"><figcaption></figcaption></figure>

## Modelo Personalizado

Para modelos que no están soportados en el nodo ChatOpenAI, puedes usar ChatOpenAI Custom. Esto permite a los usuarios introducir nombres de modelos como `mistralai/Mixtral-8x7B-Instruct-v0.1`

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-a7f2b6841aa006ebf3db3312181b75bb95149868%2Fimage%20(84).png?alt=media" alt=""><figcaption></figcaption></figure>

## Subida de Imágenes

También puedes permitir que las imágenes sean subidas y analizadas por el LLM. Internamente, Flowise utilizará el modelo [OpenAI Vision](https://platform.openai.com/docs/guides/vision) para procesar la imagen. Solo funciona con LLMChain, Conversation Chain, ReAct Agent y Conversational Agent.

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-c4d5738f833fab1ef64988747abf7e9a5eb914a5%2Fimage%20(3)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(2).png?alt=media" alt="" width="332"><figcaption></figcaption></figure>

Desde la interfaz de chat, ahora verás un nuevo botón de subida de imágenes:

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-45c9575797ee74dbebb2da8307d9d04017240b2e%2FUntitled%20(1).png?alt=media" alt=""><figcaption></figcaption></figure>

<figure><img src="https://4068692976-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUiD7nOmFRK805sNuiieJ%2Fuploads%2Fgit-blob-3a4b62d294fc4fe700c129754f17cb72ca170109%2Fimage%20(121).png?alt=media" alt=""><figcaption></figcaption></figure>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/chat-models/azure-chatopenai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
