diff --git a/en/basic/admin-panel/ai-setting.mdx b/en/basic/admin-panel/ai-setting.mdx index 6377501..94290d0 100644 --- 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. - - -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. - +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 | - - -Make sure your Vercel account has a credit card attached, that `Credit` status is healthy, and that auto top-up is enabled. - +| **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: Choose the default model for AI Chat. - - Complete the Vercel setup and confirm that public access is ready. + + Confirm the Agent Runtime configuration status, then complete the App Builder access checks. ### Configure LLM API -Start by choosing how you want to connect your models in **LLM API**. - - - - Enter your **AI Gateway API key**, then click **Test**. After the test succeeds, continue to the next step. - - - Add at least one custom provider, add the models it supports, and complete the model test. - - +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 @@ -88,7 +60,7 @@ 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 @@ -96,26 +68,25 @@ You should choose a stable model that supports tool calling and has already been 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. - - 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. + + Confirm that the current deployment includes the required Agent Runtime configuration. - - In **App Builder**, enter the **Vercel access token** under **Vercel Deploy**. This is the core setting required to publish apps. + + Confirm **Test Public Access**, then configure optional App Builder settings such as custom domain and app sign-in if you need them. -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. - + -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. -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. - - -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**. - - -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. - - diff --git a/en/basic/ai/app-builder.mdx b/en/basic/ai/app-builder.mdx index 952893c..8f19e75 100644 --- 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 - 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. 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 index 8513a30..8464867 100644 --- 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. --- Available for Pro plan and above -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. -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. - - -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. - - -| 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 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 `/`. -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. +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. -Common Base URL examples: +Common Base URL examples for supported model calls: | Provider | Base URL Format | |----------|----------------| @@ -106,7 +90,7 @@ Common Base URL examples: Model names must match the provider documentation exactly and are case-sensitive. Separate multiple models with English commas. -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 -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. diff --git a/zh/basic/admin-panel/ai-setting.mdx b/zh/basic/admin-panel/ai-setting.mdx index 6a01444..e33c1b3 100644 --- a/zh/basic/admin-panel/ai-setting.mdx +++ b/zh/basic/admin-panel/ai-setting.mdx @@ -1,6 +1,6 @@ --- title: "AI 配置" -description: "为私有化部署实例配置 AI Chat、AI 字段、AI 自动化和应用构建器。" +description: "为私有化部署实例配置 AI 对话、AI 字段、AI 自动化和应用构建器。" --- {/* mintlify-resync: 2026-05-14 */} @@ -12,32 +12,14 @@ description: "为私有化部署实例配置 AI Chat、AI 字段、AI 自动化 ## 开始前的准备 -在进入 AI 配置页之前，先确认下面这些准备项已经就绪。**AI 聊天运行环境** 和 **应用构建器** 都依赖 Vercel。 - - -只需要一个 Vercel 账户，就可以完成这些配置。 - -当前版本中，如果实例无法访问 Vercel，部分 **AI** 和 **应用构建器** 能力会受影响。Teable 正在推进 AI 和应用构建器的完整私有化部署支持，后续版本将不再依赖 Vercel 服务。 - +在进入 AI 配置页之前，先确认下面这些准备项已经就绪。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。 | 准备项 | 是否必需 | 说明 | |------|------|------| -| **Vercel 账户** | 必需 | 需要一个可用的 Vercel 账户 | -| **Vercel API 密钥** | 必需 | 用于 **AI 聊天运行环境** | -| **Team / Project** | 必需 | 需要一个可用的 Team 和 Project；如果还没有，也可以在 Vercel 中创建 | -| **AI Gateway API 密钥** | 使用 AI Gateway 时 | 只在选择 **AI Gateway** 作为模型服务商时需要 | +| **Agent Runtime 配置** | AI 对话和应用构建器必需 | 用于 AI 对话和应用构建器 | +| **自定义服务商** | 可选 | 用于已支持的模型调用 | | **OpenAI Realtime API Key** | 可选 | 只有需要在 AI 对话中启用 **语音输入** 时才需要 | -| **公网访问** | 必需 | **Teable 实例** 和 **对象存储（MinIO / S3）** 需要被公网访问 | - -Vercel 相关费用主要分成两部分： - -| 项目 | 说明 | -|------|------| -| **Vercel 基础费用** | 约为 **$20/月**，用于 App 部署和 AI 运行环境相关基础设施 | -| **AI Gateway 模型调用费用** | 按实际调用量单独计费 | - -请确认 Vercel 账户已绑定信用卡，`Credit` 状态正常，并已开启自动充值。 - +| **公网访问** | 应用发布和附件访问必需 | **Teable 实例** 和 **对象存储（MinIO / S3）** 需要被公网访问 | ## 配置步骤 @@ -55,23 +37,14 @@ Vercel 相关费用主要分成两部分： 为 AI 对话指定默认模型。 - - 完成 Vercel 相关配置，并确认公网访问准备项已经满足。 + + 确认 Agent Runtime 配置状态，再完成应用构建器的访问检查。 ### 配置 LLM API -先在 **LLM API** 中选择模型接入方式。 - - - - 填写 **AI Gateway API 密钥** 后，点击 **测试**。测试通过后，再继续后面的步骤。 - - - 添加至少一个自定义服务商，填入它支持的模型，并完成模型测试。 - - +在 **LLM API** 中添加或确认已支持的模型调用所使用的模型服务商。如果添加自定义服务商，请填入它支持的模型，并完成模型测试。 ### 配置推荐模型 @@ -87,7 +60,7 @@ Vercel 相关费用主要分成两部分： 这里要为侧边栏 **AI 对话** 指定默认模型。这个模型需要从推荐模型列表中选择，所以如果这一步是灰的，通常说明前一步还没完成。 -这里应选择支持工具调用、并且已经过测试的稳定模型，否则 Agent 能力会明显受限。 +这里建议选择已经完成测试、表现稳定的模型。 ### 可选：配置语音输入 @@ -95,26 +68,25 @@ Vercel 相关费用主要分成两部分： 你可以调整 **单次最长时长（秒）** 和 **每用户每分钟签发次数**。启用并保存语音输入后，用户会在 AI 对话输入框中看到麦克风按钮。 -### 配置运行环境与应用构建器 +### 配置 Agent Runtime 与应用构建器 -先完成 **AI 聊天运行环境**，再完成 **应用构建器**。 +私有化部署如需使用 **AI 对话** 和 **应用构建器**，需要先完成 Agent Runtime 配置。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。 - - 在 **AI 聊天运行环境** 中，先填写并验证 **Vercel API 密钥**，再选择 **Team** 和 **Project**，点击 **保存**，然后点击 **测试连接**。配置测试通过后，右侧对应的待配置项会变绿。 + + 确认当前部署已包含所需的 Agent Runtime 配置。 - - 在 **应用构建器** 中的 **Vercel 部署** 填写 **Vercel 访问令牌**。这是发布应用所需的核心配置。 + + 确认 **测试公网访问** 通过，再按需配置自定义域名、应用登录等可选项。 -如果你还需要自定义域名，或者你的服务器不能直接访问 Vercel API，可以再补充下面这些可选配置： +如有需要，可以继续补充下面这些应用构建器可选配置： | 可选项 | 什么时候需要 | |------|------| | **自定义域名** | 需要把应用发布到自己的域名下 | | **应用登录** | 生成的应用需要支持 **邮箱验证码** 或 **Google** 登录时 | -| **Vercel API 代理地址** | 服务器不能直接访问 Vercel API，或需要通过代理、网关访问 | 在 **应用登录** 中，可以为生成的应用配置登录提供方： @@ -144,34 +116,14 @@ Vercel 相关费用主要分成两部分： 先回看右侧 **待配置项**，确认缺的是哪一项。很多时候不是当前这一步没保存，而是前面的配置还没有补齐。 - + -这通常表示 **AI 聊天运行环境** 还没完成。请确认下面三项都已经填写完成： - -- **Vercel API 密钥** -- **Team** -- **Project** - -只填写 Token 还不够。选择 **Team** 和 **Project** 后，需要先保存，再测试连接。 +请检查当前部署是否已完成 Agent Runtime 配置。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。 -先检查 Vercel 账户里的 `Credit` 或余额状态，必要时充值，并确认已经开启自动充值。 +请检查当前模型服务对应的账户或服务商额度，必要时充值或调整模型配置。 - - -如果你使用的是 **Vercel AI Gateway**，请求数据仍会发送到你选择的模型服务商进行处理，因此可能会涉及第三方服务商。 - -如果你对数据安全和合规性有要求，可以在 **Vercel AI Gateway** 中开启下面这个选项： - -- **Only allow providers with Zero Data Retention (ZDR)** - -开启后，可用模型会限制在支持 **Zero Data Retention** 的服务商范围内。 - - -即使开启了 ZDR，请求仍然会发送到所选模型服务商处理；区别在于，范围会限制为支持零数据保留的服务商。 - - diff --git a/zh/basic/ai/app-builder.mdx b/zh/basic/ai/app-builder.mdx index 170c59b..1b0701e 100644 --- a/zh/basic/ai/app-builder.mdx +++ b/zh/basic/ai/app-builder.mdx @@ -230,7 +230,7 @@ Teable 自动跟踪每一次部署。 - 如果您使用私有化部署的 Teable，请参考 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面完成配置。应用构建器依赖的 **AI 聊天运行环境**、**Vercel 部署配置**、**公网访问测试** 以及相关排查说明，均以该页面为准。 + 如果您使用私有化部署的 Teable，请参考 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面完成配置。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。 发布前，请先确认 Teable 和对象存储（MinIO / S3）都能被公网访问；不确定时，可以在 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面使用 **测试公网访问** 进行验证。 diff --git a/zh/basic/ai/custom-model.mdx b/zh/basic/ai/custom-model.mdx index 016cb98..d6a09b8 100644 --- a/zh/basic/ai/custom-model.mdx +++ b/zh/basic/ai/custom-model.mdx @@ -1,23 +1,19 @@ --- title: 自定义 AI 模型 -description: 在空间中开启 AI 能力并添加模型提供商，用于 AI 字段、自动化、AI Chat 和 App Builder。 +description: 为 AI 字段、自动化等功能添加自定义模型提供商。 --- Pro 版及以上适用 -自定义模型配置适用于所有 Teable AI 功能，包括 **AI Chat**、**AI 字段**、**App Builder** 和**自动化**。 +自定义模型配置适用于 **AI 字段**、**自动化** 等模型调用功能。 -自 2026 年 4 月 9 日起，Teable 的 Agent 引擎已完成升级，以提升 **AI Chat** 和 **App Builder** 的 AI Agent 能力。本次升级后，这些功能当前仅支持 Anthropic 兼容的 API 端点，**使用不兼容的端点可能会导致报错。** +2026 年 6 月 24 日，Teable 重构了 **Agent Computer**，提升了 **AI 对话** 和 **应用构建器** 中 Cuppy 的处理速度和长任务稳定性。Agent Runtime 的 BYOK 兼容正在进行中。 -- **Cloud 用户（BYOK）：** 请使用下方 [**Agent 支持范围**](#agent-支持范围) 中列出的提供商和模型组合。 -- **私有化部署用户：** 请确保您配置的 LLM 端点兼容 Anthropic 格式。您也可以等待我们后续适配 OpenAI 兼容端点后，拉取最新镜像即可。 -- **OpenAI 兼容端点支持**已在规划中，将在后续版本中推出。 - -**推荐使用 Teable Credits：** Teable Credits 当前以成本价提供，没有中间商赚差价，让您以最优惠的价格使用顶级 AI 模型，体验最流畅。 +**推荐使用 Teable Credits：** Teable Credits 当前以成本价提供，没有中间商赚差价，让您以更优惠的价格使用顶级 AI 模型，并获得更稳定的体验。 -配置完成后，添加的模型可以供当前空间内的 **AI 字段**、**自动化**、**AI Chat** 和 **App Builder** 使用。 +配置完成后，添加的模型可以供当前空间内已支持的模型调用功能使用。 ## 配置入口 @@ -38,6 +34,8 @@ description: 在空间中开启 AI 能力并添加模型提供商，用于 AI - **AI 字段** - **AI 聊天** +开启 **AI 聊天** 只表示允许空间使用聊天功能。Agent Runtime 的 BYOK 兼容正在进行中。 + ### 添加模型提供商 点击 **添加模型提供商**，填写以下信息： @@ -54,20 +52,6 @@ description: 在空间中开启 AI 能力并添加模型提供商，用于 AI className="docs-screenshot" /> -#### Agent 支持范围 - -为保证体验，请在 **AI Chat** 和 **App Builder** 中使用下方支持的模型。列表外模型可能在 **AI 字段** 或**自动化**等部分 AI 功能中可用。对于 **AI Chat** 和 **App Builder**，不支持的模型更容易出现 Agent 效果不稳定、工具能力缺失或运行时报错。如您使用范围外的端点、提供商或模型，Teable 不提供故障排查或效果支持。 - - -下表中的提供商指模型服务来源。您在 Teable 中添加模型提供商时，需要选择 Anthropic 兼容端点，并填写对应服务商的基础 URL、API 密钥和模型名称。 - - -| 模型提供商 | 支持的模型 | -|------------|------------| -| [Anthropic](https://platform.claude.com) / [OpenRouter](https://openrouter.ai) | Claude 系列 | -| [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 | - ### 测试模型能力 当前支持三种测试方式： @@ -84,9 +68,9 @@ description: 在空间中开启 AI 能力并添加模型提供商，用于 AI 请填写 API 端点地址，而不是服务商官网地址。多数 OpenAI 兼容接口需要以 `/v1` 结尾；除非服务商文档明确要求，否则不要在 URL 末尾额外加 `/`。 -Teable 不支持 coding plan 的 Key。请使用提供商后台创建的标准 API Key。因为 coding plan 的 Key 通常只能在指定的 coding 工具中使用，不能作为通用 API Key 接入 Teable。若您使用这类 Key，模型测试失败是正常现象。 +部分 Coding Plan Key 可能只允许在指定开发工具中使用，并不是标准 API Key。是否可用于第三方服务，请以对应提供商的条款和说明为准；如需接入 Teable，请使用提供商后台创建的标准 API Key。 -常见基础 URL 示例： +用于已支持的模型调用时，常见基础 URL 示例： | 提供商 | 基础 URL 格式 | |--------|--------------| @@ -107,7 +91,7 @@ description: 在空间中开启 AI 能力并添加模型提供商，用于 AI 模型名称必须与服务商文档一致，并区分大小写。多个模型之间使用英文逗号分隔。 -常见模型名称示例： +用于已支持的模型调用时，常见模型名称示例： | 提供商 | 模型名称示例 | |--------|--------------| @@ -150,7 +134,7 @@ description: 在空间中开启 AI 能力并添加模型提供商，用于 AI -Teable 不支持这类 Key。请到服务商后台重新创建标准 **API 密钥** 后再测试。 +这类 Key 可能不支持标准 API 调用，或提供商条款不允许用于第三方服务。请先查看对应 Coding Plan 的条款；如需接入 Teable，请使用服务商后台创建的标准 **API 密钥**。