teableio · HynLcc · Jul 1, 2026 · Jul 1, 2026
diff --git a/en/basic/admin-panel/ai-setting.mdx b/en/basic/admin-panel/ai-setting.mdx
@@ -12,33 +12,14 @@ The **AI Settings** page is used to configure **AI Chat**, **AI fields**, **AI a
 
 ## Before you start
 
-Before you open the AI Settings page, make sure the following items are ready. Both **AI Chat Runtime** and **App Builder** rely on Vercel.
-
-<Note>
-You only need one Vercel account to complete the setup.
-
-In the current version, some **AI** and **App Builder** capabilities are affected if the instance cannot access Vercel. Teable is working on full private deployment support for AI and App Builder, so future versions no longer depend on Vercel services.
-</Note>
+Before you open the AI Settings page, make sure the following items are ready. Self-hosted Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 
 | Requirement | Required? | Notes |
 |------|------|------|
-| **Vercel account** | Required | You need a working Vercel account |
-| **Vercel API Token** | Required | Used for **AI Chat Runtime** |
-| **Team / Project** | Required | You need a usable Team and Project. If needed, you can create them in the page |
-| **AI Gateway API key** | When using AI Gateway | Only needed if you choose **AI Gateway** as your model provider |
+| **Agent Runtime setup** | Required for AI Chat and App Builder | Used by AI Chat and App Builder |
+| **Custom provider** | Optional | Use for supported model calls |
 | **OpenAI Realtime API Key** | Optional | Only needed if you want to enable **Voice input** in AI Chat |
-| **Public access** | Required | Your **Teable instance** and **object storage (MinIO / S3)** must be publicly accessible |
-
-Vercel-related costs usually have two parts:
-
-| Item | Notes |
-|------|------|
-| **Vercel base cost** | About **$20/month** for App deployment and AI runtime infrastructure |
-| **AI Gateway model usage** | Charged separately based on actual usage |
-
-<Tip>
-Make sure your Vercel account has a credit card attached, that `Credit` status is healthy, and that auto top-up is enabled.
-</Tip>
+| **Public access** | Required for App Builder publishing and attachment access | Your **Teable instance** and **object storage (MinIO / S3)** must be publicly accessible |
 
 ## Setup steps
 
@@ -56,23 +37,14 @@ Follow these four steps:
   <Step title="Set chat model">
     Choose the default model for AI Chat.
   </Step>
-  <Step title="Configure the runtime and App Builder">
-    Complete the Vercel setup and confirm that public access is ready.
+  <Step title="Configure Agent Runtime and App Builder">
+    Confirm the Agent Runtime configuration status, then complete the App Builder access checks.
   </Step>
 </Steps>
 
 ### Configure LLM API
 
-Start by choosing how you want to connect your models in **LLM API**.
-
-<Tabs>
-  <Tab title="AI Gateway (Recommended)">
-    Enter your **AI Gateway API key**, then click **Test**. After the test succeeds, continue to the next step.
-  </Tab>
-  <Tab title="Custom provider">
-    Add at least one custom provider, add the models it supports, and complete the model test.
-  </Tab>
-</Tabs>
+In **LLM API**, add or verify the model provider used by supported model calls. If you add a custom provider, add the models it supports and complete the model test.
 
 ### Configure Recommended Models
 
@@ -88,34 +60,33 @@ This step decides which models users can choose from. Start with a clear primary
 
 This step sets the default model for sidebar **AI Chat**. The model must come from the recommended model list, so if this step is disabled, the previous step is usually incomplete.
 
-You should choose a stable model that supports tool calling and has already been tested. Otherwise, Agent capability will be noticeably limited.
+Choose a tested, stable model here.
 
 ### Optional. Configure Voice input
 
 **Voice input** lets users enter messages in AI Chat with a microphone.
 
 You can adjust **Max session duration (seconds)** and **Session creates per minute per user**. After voice input is enabled and saved, users will see the microphone button in the AI Chat input box.
 
-### Configure the Runtime and App Builder
+### Configure Agent Runtime and App Builder
 
-Complete **AI Chat Runtime** first, then complete **App Builder**.
+Self-hosted **AI Chat** and **App Builder** require Agent Runtime setup. Self-hosted Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 
 <Steps>
-  <Step title="Finish AI Chat Runtime">
-    In **AI Chat Runtime**, enter and verify the **Vercel API Token**, select **Team** and **Project**, click **Save**, then click **Test Connection**. After the connection test succeeds, the matching item in the **Pending configuration** panel will turn green.
+  <Step title="Confirm Agent Runtime status">
+    Confirm that the current deployment includes the required Agent Runtime configuration.
   </Step>
-  <Step title="Finish the basic App Builder setup">
-    In **App Builder**, enter the **Vercel access token** under **Vercel Deploy**. This is the core setting required to publish apps.
+  <Step title="Finish the App Builder setup">
+    Confirm **Test Public Access**, then configure optional App Builder settings such as custom domain and app sign-in if you need them.
   </Step>
 </Steps>
 
-If you also need a custom domain, or if your server cannot access the Vercel API directly, you can add these optional settings:
+You can add these optional App Builder settings when needed:
 
 | Optional item | When you need it |
 |------|------|
 | **Custom domain** | When you want to publish apps under your own domain |
 | **App Auth** | When generated apps need **Email OTP** or **Google** sign-in |
-| **Vercel API proxy URL** | When your server cannot reach the Vercel API directly, or when you use a proxy or gateway |
 
 In **App Auth**, you can configure sign-in providers for generated apps:
 
@@ -145,34 +116,14 @@ Go back and finish **Configure recommended models** first. The chat model can on
 Check the **Pending configuration** panel first to see which item is still missing. In many cases, the current step is saved correctly, but an earlier requirement is still incomplete.
 </Accordion>
 
-<Accordion title="The page says Vercel Sandbox configuration is still missing">
+<Accordion title="The page says Agent Runtime configuration is still missing">
 
-This usually means **AI Chat Runtime** is not fully configured yet. Make sure all three items below are completed:
-
-- **Vercel API Token**
-- **Team**
-- **Project**
-
-Entering only the token is not enough. After choosing **Team** and **Project**, save the selection before testing the connection.
+Check whether the current deployment has completed Agent Runtime setup. Self-hosted Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 </Accordion>
 
 <Accordion title="I get a credit exceeded error">
 
-Check your Vercel account `Credit` or balance first. Top up if needed, and make sure auto top-up is enabled.
+Check the account or provider used by your configured model service. Top up or change the model configuration if needed.
 </Accordion>
 
-<Accordion title="If I use Vercel AI Gateway, will AI models process my data?">
-
-If you use **Vercel AI Gateway**, request data will still be sent to the model provider you selected for processing, so third-party providers may be involved.
-
-If you have data security or compliance requirements, enable this option in **Vercel AI Gateway**:
-
-- **Only allow providers with Zero Data Retention (ZDR)**
-
-After you enable it, available models will be limited to providers that support **Zero Data Retention**.
-
-<Note>
-Even with ZDR enabled, requests are still sent to the selected model provider for processing. The difference is that usage is limited to providers that support zero data retention.
-</Note>
-</Accordion>
 </AccordionGroup>
diff --git a/en/basic/ai/app-builder.mdx b/en/basic/ai/app-builder.mdx
@@ -215,7 +215,7 @@ For prompt patterns, build tips, rollback advice, and common troubleshooting, se
   </Accordion>
 
   <Accordion title="Where do I configure App Builder for Self-Hosted?">
-    If you are running Teable self-hosted, follow the setup on the [AI Settings](/en/basic/admin-panel/ai-setting) page. That page is the source of truth for **AI Chat Runtime**, **Vercel deployment settings**, **public access testing**, and the related troubleshooting notes for App Builder.
+    If you are running Teable self-hosted, follow the setup on the [AI Settings](/en/basic/admin-panel/ai-setting) page. Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 
     <Note>
     Before publishing, make sure both your Teable instance and object storage (MinIO / S3) are publicly accessible. If you are unsure, use **Test Public Access** on the [AI Settings](/en/basic/admin-panel/ai-setting) page.

diff --git a/en/basic/ai/custom-model.mdx b/en/basic/ai/custom-model.mdx
@@ -1,23 +1,19 @@
 ---
 title: Custom AI Model
-description: Enable AI capabilities in a space and add model providers for AI Fields, Automations, AI Chat, and App Builder.
+description: Add custom model providers for AI Fields, Automations, and other supported model calls.
 ---
 
 <Tip>Available for Pro plan and above</Tip>
 
 <Note>
-Custom model configuration applies to all Teable AI features, including **AI Chat**, **AI Fields**, **App Builder**, and **Automations**.
+Custom model configuration applies to features that use model calls, such as **AI Fields** and **Automations**.
 
-Starting April 9, 2026, Teable's agent engine has been upgraded for **AI Chat** and **App Builder**. These agent-based features currently require Anthropic-compatible API endpoints. **Using an incompatible endpoint may cause errors.**
+On June 24, 2026, Teable rebuilt **Agent Computer**, improving Cuppy's processing speed and long-task stability in **AI Chat** and **App Builder**. BYOK compatibility for the Agent Runtime is in progress.
 
-- **Cloud users with BYOK:** Use one of the supported provider and model pairs listed in [**Agent Support Scope**](#agent-support-scope) below.
-- **Self-hosted users:** Please ensure your configured LLM endpoint is Anthropic-compatible. Alternatively, you can wait for our upcoming OpenAI-compatible endpoint support and pull the latest image once it's available.
-- **OpenAI-compatible endpoint support** is on our roadmap and will be added in a future release.
-
-**We recommend using Teable Credits.** Teable Credits are currently offered at cost — no middleman, no markup — giving you access to top-tier AI models at the most competitive pricing with the smoothest experience.
+**We recommend using Teable Credits.** Teable Credits are currently offered at cost, with no middleman and no markup, giving you access to top-tier AI models at competitive pricing with the smoothest experience.
 </Note>
 
-After setup, the models you add can be used by **AI Fields**, **Automations**, **AI Chat**, and **App Builder** in the current space.
+After setup, the models you add can be used by supported model calling features in the current space.
 
 ## Where to Configure It
 
@@ -38,6 +34,8 @@ Under **AI Capabilities**, turn on what you need:
 - **AI Field**
 - **AI Chat**
 
+Enabling **AI Chat** only controls whether the chat feature is available in the space. BYOK compatibility for the Agent Runtime is in progress.
+
 ### Add LLM Provider
 
 Click **Add LLM provider** and fill in the following:
@@ -54,20 +52,6 @@ Click **Add LLM provider** and fill in the following:
   className="docs-screenshot"
 />
 
-#### Agent Support Scope
-
-To use **AI Chat** and **App Builder** reliably, configure one of the supported models below. Models outside this list may still work for **AI Fields** or **Automations**, but they are not recommended for agent-based features. In **AI Chat** and **App Builder**, unsupported endpoints, providers, or models may produce weaker results, miss tool-use capabilities, or cause runtime errors. Teable does not provide troubleshooting or performance support for configurations outside this scope.
-
-<Note>
-The providers below refer to the model service source. When adding an LLM provider in Teable, select an Anthropic-compatible endpoint, then enter the corresponding Base URL, API key, and model name.
-</Note>
-
-| Model provider | Supported model |
-|----------------|-----------------|
-| [Anthropic](https://platform.claude.com) / [OpenRouter](https://openrouter.ai) | Claude series |
-| [Moonshot AI](https://platform.moonshot.ai) / [OpenRouter](https://openrouter.ai) | Kimi K2.6 |
-| [MiniMax](https://platform.minimax.io) / [OpenRouter](https://openrouter.ai) | MiniMax M2.7 |
-
 ### Test Model Capabilities
 
 There are currently three ways to test:
@@ -84,9 +68,9 @@ If a model is meant for image generation, check **Image Generation Model** befor
 
 <Warning>Use the API endpoint URL, not the provider's website URL. Most OpenAI-compatible endpoints need to end with `/v1`. Unless the provider's documentation explicitly says otherwise, do not add an extra trailing `/`.</Warning>
 
-<Warning>Teable does not support Coding Plan API keys. Please use a standard API key created in your provider dashboard. Coding Plan API keys usually only work inside specific coding tools and cannot be used as a general API key in Teable. If you use this kind of key, it is normal for model testing to fail.</Warning>
+<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 Base URL examples:
+Common Base URL examples for supported model calls:
 
 | Provider | Base URL Format |
 |----------|----------------|
@@ -106,7 +90,7 @@ Common Base URL examples:
 
 <Note>Model names must match the provider documentation exactly and are case-sensitive. Separate multiple models with English commas.</Note>
 
-Common model examples:
+Common model examples for supported model calls:
 
 | Provider | Example Models |
 |----------|----------------|
@@ -148,7 +132,7 @@ Make sure the **Models** value matches the provider documentation exactly, inclu
 </Accordion>
 
 <Accordion title="Testing fails when I use a Coding Plan key">
-Teable does not support this kind of key. Create a standard **API Key** in your provider dashboard and test again.
+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">