> ## Documentation Index
> Fetch the complete documentation index at: https://help.teable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom AI Model

> Add custom model providers for AI Fields, Automations, AI Chat, App Builder, and other supported AI features.

<Tip>Available for Pro plan and above</Tip>

## Where to Configure It

1. Open the target space.
2. Click **Settings** in the top right corner.
3. Go to **AI settings**.

<img src="https://mintcdn.com/teablecn/TO9j-Q8_3sjEReNV/images/docs/ai/2026-05-21-custom-model-ai-settings.png?fit=max&auto=format&n=TO9j-Q8_3sjEReNV&q=85&s=719ff403a81baa5e91656734a04469d4" alt="AI settings page" className="docs-screenshot" width="1600" height="978" data-path="images/docs/ai/2026-05-21-custom-model-ai-settings.png" />

## Setup Steps

Under **AI Capabilities**, turn on what you need:

* **AI Field**
* **AI Chat**

Enabling **AI Chat** controls whether the chat feature is available in the space.

### Add LLM Provider

<Note>
  When you add a new LLM provider, choose **OpenAI**, **Anthropic**, or **OpenAI Compatible** as the provider type. Use **OpenAI Compatible** for services that expose an OpenAI-compatible API endpoint. If a task uses images, screenshots, or other visual input, choose a model with vision support. Models without vision support will fail on these multimodal tasks.
</Note>

Click **Add LLM provider** and fill in the following:

* **Name**: Used to distinguish different providers.
* **Provider type**: Select the provider type.
* **Base URL**: Enter the provider's API endpoint.
* **API Key**: Enter the API key from the provider.
* **Models**: Enter the model names you want to connect. Separate multiple models with English commas.

<img src="https://mintcdn.com/teablecn/TO9j-Q8_3sjEReNV/images/docs/ai/2026-05-21-custom-model-add-provider.png?fit=max&auto=format&n=TO9j-Q8_3sjEReNV&q=85&s=6f34465ed2c68d3f5f64280bb77d9a5e" alt="Add LLM provider dialog" className="docs-screenshot" width="1600" height="974" data-path="images/docs/ai/2026-05-21-custom-model-add-provider.png" />

### Test Model Capabilities

There are currently three ways to test:

* Click **Test** on the LLM provider row.
* Click **Test** on an individual model row.
* Click **Test Model Capabilities** in the top-right corner of the list to batch-test all configured models.

If a model is meant for image generation, check **Image Generation Model** before running the test. Once checked, Teable tests it as an image model for text-to-image and image-to-image capabilities. If it is not checked, the model is tested as a regular text model.

## Configuration Tips

### Base URL and Models

<Warning>Some Coding Plan keys may only work in designated coding tools and may not be standard API keys. Check the provider's terms before using them with third-party services. To connect Teable, use a standard API key created in the provider dashboard.</Warning>

Common examples:

| Provider type     | Base URL format                                 | Example models                                     |
| ----------------- | ----------------------------------------------- | -------------------------------------------------- |
| OpenAI            | `https://api.openai.com/v1`                     | `gpt-5.5,o3,gpt-5-mini`                            |
| Anthropic         | `https://api.anthropic.com/v1`                  | `claude-opus-4-8,claude-sonnet-5,claude-haiku-4-5` |
| OpenAI Compatible | The provider's OpenAI-compatible `/v1` endpoint | `gpt-5.5,gpt-5.4,o3,gpt-5-mini`                    |

<Note>Model names must match the provider documentation exactly and are case-sensitive. Separate multiple models with English commas.</Note>

Notes:

* Model names are case-sensitive. Use the exact names from the provider documentation.
* Some providers require no spaces after commas, for example `gpt-5.5,o3`.
* For **OpenAI Compatible** providers, use the model naming format required by that provider. Some services use `provider/model-name`.

## FAQ

<AccordionGroup>
  <Accordion title="All model tests failed">
    Check whether the **Base URL** is correct, whether it was mistakenly filled with the provider homepage URL, or whether it has an extra trailing `/`. If you are using an OpenAI-compatible endpoint, also confirm that `/v1` is not missing.
  </Accordion>

  <Accordion title="I get a “Test failed” error">
    Check whether the **API Key** is valid and whether the account still has credits or permission to call the model.
  </Accordion>

  <Accordion title="Connection timeout">
    Check whether the **Base URL** is correct and whether your current environment can reach that address.
  </Accordion>

  <Accordion title="Model not found">
    Make sure the **Models** value matches the provider documentation exactly, including case and separator format.
  </Accordion>

  <Accordion title="Testing fails when I use a Coding Plan key">
    This kind of key may not support standard API calls, or the provider's terms may not allow third-party service use. Check the provider's Coding Plan terms first. To connect Teable, use a standard **API Key** created in the provider dashboard.
  </Accordion>

  <Accordion title="The image generation model test result looks wrong">
    If the model is meant for image generation, check **Image Generation Model** first and then test again. Once checked, Teable tests text-to-image and image-to-image capabilities instead.
  </Accordion>
</AccordionGroup>