---
title: Connect to OpenAI
description: This page provides step-by-step instructions for connecting Kibana to OpenAI’s large language models (LLMs). You’ll first need to create an OpenAI API...
url: https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/8924/explore-analyze/ai-features/llm-guides/connect-to-openai
products:
- Elastic Cloud Serverless
- Elastic Documentation
- Elastic Security
applies_to:
- Serverless Security projects: Generally available
- Elastic Stack: Generally available
---
# Connect to OpenAI
This page provides step-by-step instructions for connecting Kibana to OpenAI’s large language models (LLMs). You’ll first need to create an OpenAI API key, then connect Kibana to OpenAI.
## Configure OpenAI
### Select a model
Before creating an API key, you must choose a model. Refer to the [OpenAI docs](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4) to select a model. Take note of the specific model name (for example `gpt-4-turbo`); you’ll need it when configuring Kibana.
`GPT-4o` offers increased performance over previous versions. For more information on how different models perform for different tasks, refer to the [Large language model performance matrix](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/8924/solutions/security/ai/large-language-model-performance-matrix).
### Create an API key
To generate an API key:
1. Log in to the OpenAI platform and navigate to **API keys**.
2. Select **Create new secret key**.
3. Name your key, select an OpenAI project, and set the desired permissions.
4. Click **Create secret key** and then copy and securely store the key. It will not be accessible after you leave this screen.
The following video demonstrates these steps (click to watch).
[](https://videos.elastic.co/watch/vbD7fGBGgyxK4TRbipeacL?)
## Connect Kibana to OpenAI
Create an inference endpoint so that Kibana can use models from OpenAI. AI features in Kibana can use only endpoints with the `chat_completion` task type. For more information about adding endpoints, refer to [External inference](/elastic/docs-content/pull/8924/explore-analyze/elastic-inference/external#add-inference-endpoints).
1. Go to the **External inference** page by using the navigation menu or the [global search field](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/8924/explore-analyze/find-and-organize/find-apps-and-objects).
2. Select **Add endpoint**.
3. Select **OpenAI** as the service.
1. For **API Key**, paste the API key that you created.
2. For **Model ID**, enter the name of the [model](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4) you want to use. The **URL** field is optional.
3. Select the `chat_completion` task type, then select **Save**.
Create an OpenAI connector so that Kibana can use OpenAI models.
1. Log in to Kibana.
2. Find the **Connectors** page in the navigation menu or use the [global search field](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/8924/explore-analyze/find-and-organize/find-apps-and-objects). Then click **Create Connector**, and select **OpenAI**.
3. Provide a name for your connector, such as `OpenAI (GPT-4 Turbo Preview)`, to help keep track of the model and version you are using.
4. Under **Select an OpenAI provider**, choose **OpenAI**.
5. The **URL** field can be left as default.
6. Under **Default model**, specify which [model](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4) you want to use.
7. Paste the API key that you created into the corresponding field.
8. Click **Save**.
The following video demonstrates these steps (click to watch).[](https://videos.elastic.co/watch/BGaQ73KBJCzeqWoxXkQvy9?)