@lobehub/chat 1.135.6 → 1.136.0

package/CHANGELOG.md

@@ -2,6 +2,39 @@
 
 # Changelog
 
+## [Version 1.136.0](https://github.com/lobehub/lobe-chat/compare/v1.135.6...v1.136.0)
+
+<sup>Released on **2025-10-09**</sup>
+
+#### ✨ Features
+
+- **misc**: Add new provider Cerebras.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix standalone plugin rerender issue.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's improved
+
+- **misc**: Add new provider Cerebras, closes [#9559](https://github.com/lobehub/lobe-chat/issues/9559) ([9cceaad](https://github.com/lobehub/lobe-chat/commit/9cceaad))
+
+#### What's fixed
+
+- **misc**: Fix standalone plugin rerender issue, closes [#9611](https://github.com/lobehub/lobe-chat/issues/9611) [#9396](https://github.com/lobehub/lobe-chat/issues/9396) ([7ab30fc](https://github.com/lobehub/lobe-chat/commit/7ab30fc))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.135.6](https://github.com/lobehub/lobe-chat/compare/v1.135.5...v1.135.6)
 
 <sup>Released on **2025-10-08**</sup>

package/Dockerfile.database

@@ -302,6 +302,8 @@ ENV \
     BFL_API_KEY="" BFL_MODEL_LIST="" \
     # Vercel AI Gateway
     VERCELAIGATEWAY_API_KEY="" VERCELAIGATEWAY_MODEL_LIST=""
+    # Cerebras
+    CEREBRAS_API_KEY="" CEREBRAS_MODEL_LIST=""
 
 USER nextjs
 

package/changelog/v1.json

@@ -1,4 +1,16 @@
 [
+  {
+    "children": {
+      "features": [
+        "Add new provider Cerebras."
+      ],
+      "fixes": [
+        "Fix standalone plugin rerender issue."
+      ]
+    },
+    "date": "2025-10-09",
+    "version": "1.136.0"
+  },
   {
     "children": {},
     "date": "2025-10-08",

package/docs/development/basic/feature-development-frontend.mdx

@@ -5,7 +5,9 @@ LobeChat is built on the Next.js framework and uses TypeScript as the primary de
 1. Routing: Define routes (`src/app`).
 2. Data Structure: Define data structures (`src/types`).
 3. Business Logic Implementation: Zustand store (`src/store`).
-4. Page Display: Write static components/pages (`src/app/<new-page>/features/<new-feature>.tsx`).
+4. Page Display: Write static components/pages. Create features in:
+   - `src/features/<feature-name>/` for **shared global features** (used across multiple pages)
+   - `src/app/<new-page>/features/<feature-name>/` for **page-specific features** (only used in this page)
 5. Function Binding: Bind the store with page triggers (`const [state, function] = useNewStore(s => [s.state, s.function])`).
 
 Taking the "Chat Messages" feature as an example, here are the brief steps to implement this feature:
@@ -60,7 +62,8 @@ export const useChatStore = create<ChatState>((set) => ({
 In `src/app/<new-page>/features/<new-feature>.tsx`, we need to create a new page or component to display "Chat Messages". In this file, we can use the Zustand Store created earlier and Ant Design components to build the UI:
 
 ```jsx
-// src/features/chat/index.tsx
+// src/app/chat/features/ChatPage/index.tsx
+// Note: Use src/app/<page>/features/ for page-specific components
 import { List, Typography } from 'antd';
 import { useChatStore } from 'src/store/chatStore';
 
@@ -82,6 +85,12 @@ const ChatPage = () => {
 export default ChatPage;
 ```
 
+> **Note on Feature Organization**: LobeChat uses two patterns for organizing features:
+> - **Global features** (`src/features/`): Shared components like `ChatInput`, `Conversation` used across the app
+> - **Page-specific features** (`src/app/<page>/features/`): Components used only within a specific page route
+>
+> Choose based on reusability. If unsure, start with page-specific and refactor to global if needed elsewhere.
+
 ## 5. Function Binding
 
 In a page or component, we need to bind the Zustand Store's state and methods to the UI. In the example above, we have already bound the `messages` state to the `dataSource` property of the list. Now, we also need a method to add new messages. We can define this method in the Zustand Store and then use it in the page or component:

package/docs/development/basic/feature-development-frontend.zh-CN.mdx

@@ -5,7 +5,9 @@ LobeChat 基于 Next.js 框架构建，使用 TypeScript 作为主要开发语
 1. 路由：定义路由 (`src/app`)
 2. 数据结构： 定义数据结构 ( `src/types` )
 3. 业务功能实现： zustand store (`src/store`)
-4. 页面展示：书写静态组件 / 页面 (`src/app/<new-page>/features/<new-feature>.tsx`)
+4. 页面展示：书写静态组件 / 页面。根据以下方式创建功能组件：
+   - `src/features/<feature-name>/` 用于 **全局共享功能**（跨多个页面使用）
+   - `src/app/<new-page>/features/<feature-name>/` 用于 **页面专属功能**（仅在当前页面使用）
 5. 功能绑定：绑定 store 与页面的触发 (`const  [state,function]= useNewStore(s=>[s.state,s.function])`)
 
 我们以 "会话消息" 功能为例，以下是实现这个功能的简要步骤：
@@ -60,7 +62,8 @@ export const useChatStore = create<ChatState>((set) => ({
 在 `src/app/<new-page>/features/<new-feature>.tsx` 中，我们需要创建一个新的页面或组件来显示 "会话消息"。在这个文件中，我们可以使用上面创建的 Zustand Store，以及 Ant Design 的组件来构建 UI：
 
 ```jsx
-// src/features/chat/index.tsx
+// src/app/chat/features/ChatPage/index.tsx
+// 注意：使用 src/app/<page>/features/ 放置页面专属组件
 import { List, Typography } from 'antd';
 import { useChatStore } from 'src/store/chatStore';
 
@@ -82,6 +85,12 @@ const ChatPage = () => {
 export default ChatPage;
 ```
 
+> **关于功能组件组织方式的说明**：LobeChat 使用两种模式来组织功能组件：
+> - **全局功能**（`src/features/`）：跨应用共享的组件，如 `ChatInput`、`Conversation` 等
+> - **页面专属功能**（`src/app/<page>/features/`）：仅在特定页面路由中使用的组件
+>
+> 根据可复用性选择合适的方式。如果不确定，可以先放在页面专属位置，需要时再重构为全局共享。
+
 ## 5. 功能绑定
 
 在页面或组件中，我们需要将 Zustand Store 的状态和方法绑定到 UI 上。在上面的示例中，我们已经将 `messages` 状态绑定到了列表的 `dataSource` 属性上。现在，我们还需要一个方法来添加新的消息。我们可以在 Zustand Store 中定义这个方法，然后在页面或组件中使用它：

package/docs/self-hosting/environment-variables/model-provider.mdx

@@ -717,4 +717,20 @@ NewAPI is a multi-provider model aggregation service that supports automatic mod
 - Default: `-`
 - Example: `-all,+vercel-model-1,+vercel-model-2=vercel-special`
 
+## Cerebras
+
+### `CEREBRAS_API_KEY`
+
+- Type: Required
+- Description: This is the API key you applied for in the Cerebras service.
+- Default: -
+- Example: `csk-xxxxxx...xxxxxx`
+
+### `CEREBRAS_MODEL_LIST`
+
+- Type: Optional
+- Description: Used to control the Cerebras model list. Use `+` to add a model, `-` to hide a model, and `model_name=display_name` to customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists.
+- Default: `-`
+- Example: `-all,+cerebras-model-1,+cerebras-model-2=cerebras-special`
+
 [model-list]: /docs/self-hosting/advanced/model-list

package/docs/self-hosting/environment-variables/model-provider.zh-CN.mdx

@@ -720,4 +720,20 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 - 默认值：`-`
 - 示例：`-all,+vercel-model-1,+vercel-model-2=vercel-special`
 
+## Cerebras
+
+### `CEREBRAS_API_KEY`
+
+- 类型：必选
+- 描述：这是你在 Cerebras 服务中申请的 API 密钥
+- 默认值：-
+- 示例：`csk-xxxxxx...xxxxxx`
+
+### `CEREBRAS_MODEL_LIST`
+
+- 类型：可选
+- 描述：用来控制 Cerebras 模型列表，使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名=展示名` 来自定义模型的展示名，用英文逗号隔开。模型定义语法规则与其他 provider 保持一致。
+- 默认值：`-`
+- 示例：`-all,+cerebras-model-1,+cerebras-model-2=cerebras-special`
+
 [model-list]: /zh/docs/self-hosting/advanced/model-list

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.135.6",
+  "version": "1.136.0",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",

package/packages/model-bank/package.json

@@ -15,6 +15,7 @@
     "./baichuan": "./src/aiModels/baichuan.ts",
     "./bedrock": "./src/aiModels/bedrock.ts",
     "./bfl": "./src/aiModels/bfl.ts",
+    "./cerebras": "./src/aiModels/cerebras.ts",
     "./cloudflare": "./src/aiModels/cloudflare.ts",
     "./cohere": "./src/aiModels/cohere.ts",
     "./cometapi": "./src/aiModels/cometapi.ts",

package/packages/model-bank/src/aiModels/cerebras.ts

@@ -0,0 +1,156 @@
+import { AIChatModelCard } from '../types/aiModel';
+
+const cerebrasModels: AIChatModelCard[] = [
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 32_768,
+    description: 'Llama 4 Scout：高性能的 Llama 系列模型，适合需高吞吐与低延迟的场景。',
+    displayName: 'Llama 4 Scout',
+    id: 'llama-4-scout-17b-16e-instruct',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.65, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 0.85, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 32_768,
+    description:
+      'Llama 4 Maverick：高性能的 Llama 系列模型，适合高级推理、复杂问题解决和指令跟随任务。',
+    displayName: 'Llama 4 Maverick',
+    id: 'llama-4-maverick-17b-128e-instruct',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.2, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 32_768,
+    description: 'Llama 3.1 8B：小体量、低延迟的 Llama 变体，适合轻量在线推理与交互场景。',
+    displayName: 'Llama 3.1 8B',
+    id: 'llama3.1-8b',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 131_072,
+    description: 'Llama 3.3 70B：中大型 Llama 模型，兼顾推理能力与吞吐。',
+    displayName: 'Llama 3.3 70B',
+    id: 'llama-3.3-70b',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.85, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 1.2, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+    },
+    contextWindowTokens: 131_072,
+    displayName: 'GPT OSS 120B',
+    enabled: true,
+    id: 'gpt-oss-120b',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.35, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 0.75, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    settings: {
+      extendParams: ['reasoningEffort'],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+    },
+    contextWindowTokens: 131_072,
+    description: 'Qwen 3 32B：Qwen 系列在多语言与编码任务上表现优良，适合中等规模生产化使用。',
+    displayName: 'Qwen 3 32B',
+    id: 'qwen-3-32b',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 131_072,
+    displayName: 'Qwen 3 235B Instruct',
+    id: 'qwen-3-235b-a22b-instruct-2507',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 1.2, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      reasoning: true,
+    },
+    contextWindowTokens: 131_072,
+    displayName: 'Qwen 3 235B Thinking',
+    id: 'qwen-3-235b-a22b-thinking-2507',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 2.9, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 131_072,
+    description: 'Qwen 3 Coder 480B：面向代码生成与复杂编程任务的长上下文模型。',
+    displayName: 'Qwen 3 Coder 480B',
+    id: 'qwen-3-coder-480b',
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    type: 'chat',
+  },
+];
+
+export const allModels = [...cerebrasModels];
+
+export default allModels;

package/packages/model-bank/src/aiModels/hunyuan.ts

@@ -509,7 +509,7 @@ const hunyuanChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 40_000,
     description:
-      '混元多模态理解深度思考模型，支持多模态原生长思维链，擅长处理各种图片推理场景，在理科难题上相比快思考模型全面提升。',
+      '混元最新版 t1-vision 视觉深度思考模型，相比上一版模型在通用图文问答、视觉定位、OCR、图表、拍题解题、看图创作等任务上全面提升，显著优化了英文和小语种能力。',
     displayName: 'Hunyuan T1 Vision 20250916',
     id: 'hunyuan-t1-vision-20250916',
     maxOutput: 16_000,

package/packages/model-bank/src/aiModels/index.ts

@@ -10,6 +10,7 @@ import { default as azureai } from './azureai';
 import { default as baichuan } from './baichuan';
 import { default as bedrock } from './bedrock';
 import { default as bfl } from './bfl';
+import { default as cerebras } from './cerebras';
 import { default as cloudflare } from './cloudflare';
 import { default as cohere } from './cohere';
 import { default as cometapi } from './cometapi';
@@ -95,6 +96,7 @@ export const LOBE_DEFAULT_MODEL_LIST = buildDefaultModelList({
   baichuan,
   bedrock,
   bfl,
+  cerebras,
   cloudflare,
   cohere,
   cometapi,
@@ -161,6 +163,7 @@ export { default as azureai } from './azureai';
 export { default as baichuan } from './baichuan';
 export { default as bedrock } from './bedrock';
 export { default as bfl } from './bfl';
+export { default as cerebras } from './cerebras';
 export { default as cloudflare } from './cloudflare';
 export { default as cohere } from './cohere';
 export { default as cometapi } from './cometapi';

package/packages/model-bank/src/aiModels/nebius.ts

@@ -154,23 +154,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-    },
-    contextWindowTokens: 40_960,
-    displayName: 'Qwen3-235B-A22B',
-    id: 'Qwen/Qwen3-235B-A22B',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.2, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -188,23 +171,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-    },
-    contextWindowTokens: 40_960,
-    displayName: 'Qwen3-30B-A3B (fast)',
-    id: 'Qwen/Qwen3-30B-A3B-fast',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.9, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -256,23 +222,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-    },
-    contextWindowTokens: 40_960,
-    displayName: 'Qwen3-4B (fast)',
-    id: 'Qwen/Qwen3-4B-fast',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.08, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.24, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -338,39 +287,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-    },
-    contextWindowTokens: 163_840,
-    displayName: 'DeepSeek-R1',
-    id: 'deepseek-ai/DeepSeek-R1',
-    organization: 'deepseek',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 2.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 163_840,
-    displayName: 'DeepSeek-R1 (fast)',
-    id: 'deepseek-ai/DeepSeek-R1-fast',
-    organization: 'deepseek',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 6, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -403,22 +319,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Meta-Llama-3.1-70B-Instruct',
-    id: 'meta-llama/Meta-Llama-3.1-70B-Instruct',
-    organization: 'meta',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.13, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -467,35 +367,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    contextWindowTokens: 128_000,
-    displayName: 'Mistral-Nemo-Instruct-2407',
-    id: 'mistralai/Mistral-Nemo-Instruct-2407',
-    organization: 'mistralai',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.04, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.12, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 32_768,
-    displayName: 'Qwen2.5-Coder-7B',
-    id: 'Qwen/Qwen2.5-Coder-7B',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.01, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.03, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -512,38 +383,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Qwen2.5-Coder-32B-Instruct',
-    id: 'Qwen/Qwen2.5-Coder-32B-Instruct',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.06, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.18, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Qwen2.5-Coder-32B-Instruct (fast)',
-    id: 'Qwen/Qwen2.5-Coder-32B-Instruct-fast',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     contextWindowTokens: 8192,
     displayName: 'Gemma-2-2b-it',
@@ -573,38 +412,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Qwen2.5-32B-Instruct',
-    id: 'Qwen/Qwen2.5-32B-Instruct',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.06, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.2, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Qwen2.5-32B-Instruct (fast)',
-    id: 'Qwen/Qwen2.5-32B-Instruct-fast',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.13, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -621,38 +428,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Qwen2.5-72B-Instruct (fast)',
-    id: 'Qwen/Qwen2.5-72B-Instruct-fast',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.25, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.75, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 8192,
-    displayName: 'Llama3-OpenBioLLM-70B',
-    id: 'aaditya/Llama3-OpenBioLLM-70B',
-    organization: 'aaditya',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.13, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -687,22 +462,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 16_384,
-    displayName: 'phi-4',
-    id: 'microsoft/phi-4',
-    organization: 'microsoft',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -751,23 +510,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'DeepSeek-R1-Distill-Llama-70B',
-    id: 'deepseek-ai/DeepSeek-R1-Distill-Llama-70B',
-    organization: 'deepseek',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.25, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.75, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -784,22 +526,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Llama-3_3-Nemotron-Super-49B-v1',
-    id: 'nvidia/Llama-3_3-Nemotron-Super-49B-v1',
-    organization: 'nvidia',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.13, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -865,40 +591,6 @@ const nebiusChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      vision: true,
-    },
-    contextWindowTokens: 32_768,
-    displayName: 'Qwen2-VL-72B-Instruct',
-    id: 'Qwen/Qwen2-VL-72B-Instruct',
-    organization: 'Qwen',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.13, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-      vision: true,
-    },
-    contextWindowTokens: 131_072,
-    displayName: 'Mistral-Small-3.1-24B-Instruct-2503',
-    id: 'mistralai/Mistral-Small-3.1-24B-Instruct-2503',
-    organization: 'mistralai',
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 0.05, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 0.15, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -977,17 +669,6 @@ const nebiusChatModels: AIChatModelCard[] = [
 //     },
 //     type: 'image',
 //   },
-//   {
-//     contextWindowTokens: 0,
-//     displayName: 'Stable Diffusion XL 1.0',
-//     id: 'stability-ai/sdxl',
-//     pricing: {
-//       units: [
-//         { name: 'imageGeneration', rate: 0.003, strategy: 'fixed', unit: 'image' },
-//       ],
-//     },
-//     type: 'image',
-//   },
 // ];
 
 // export const nebiusEmbeddingModels: AIEmbeddingModelCard[] = [

package/packages/model-bank/src/aiModels/ollamacloud.ts

@@ -1,6 +1,19 @@
 import { AIChatModelCard } from '../types/aiModel';
 
 const ollamaCloudModels: AIChatModelCard[] = [
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+    },
+    contextWindowTokens: 200_000,
+    description:
+      '智谱最新旗舰模型 GLM-4.6 (355B) 在高级编码、长文本处理、推理与智能体能力上全面超越前代，尤其在编程能力上对齐 Claude Sonnet 4，成为国内顶尖的 Coding 模型。',
+    displayName: 'GLM-4.6',
+    enabled: true,
+    id: 'glm4.6:355b',
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,

package/packages/model-bank/src/aiModels/vercelaigateway.ts

@@ -73,7 +73,6 @@ const vercelAIGatewayChatModels: AIChatModelCard[] = [
     description:
       'Claude Sonnet 4 在 Sonnet 3.7 的行业领先能力基础上进行了显著改进，在编码方面表现出色，在 SWE-bench 上达到了最先进的 72.7%。该模型在性能和效率之间取得了平衡，适用于内部和外部用例，并通过增强的可控性实现对实现的更大控制。',
     displayName: 'Claude Sonnet 4',
-    enabled: true,
     id: 'anthropic/claude-sonnet-4',
     pricing: {
       units: [
@@ -118,7 +117,6 @@ const vercelAIGatewayChatModels: AIChatModelCard[] = [
     description:
       'OpenAI 的 o3 是最强大的推理模型，在编码、数学、科学和视觉感知方面设立了新的最先进水平。它擅长需要多方面分析的复杂查询，在分析图像、图表和图形方面具有特殊优势。',
     displayName: 'o3',
-    enabled: true,
     id: 'openai/o3',
     pricing: {
       units: [
@@ -448,7 +446,6 @@ const vercelAIGatewayChatModels: AIChatModelCard[] = [
     description:
       'GLM-4.5 系列模型是专门为智能体设计的基础模型。旗舰 GLM-4.5 集成了 3550 亿总参数（320 亿活跃），统一了推理、编码和代理能力以解决复杂的应用需求。作为混合推理系统，它提供双重操作模式。',
     displayName: 'GLM-4.5',
-    enabled: true,
     id: 'zai/glm-4.5',
     pricing: {
       units: [

package/packages/model-bank/src/aiModels/xai.ts

@@ -160,29 +160,6 @@ const xaiChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      search: true,
-    },
-    contextWindowTokens: 131_072,
-    description:
-      '旗舰级模型，擅长数据提取、编程和文本摘要等企业级应用，拥有金融、医疗、法律和科学等领域的深厚知识。',
-    displayName: 'Grok 3 (Fast mode)',
-    id: 'grok-3-fast', // legacy
-    pricing: {
-      units: [
-        { name: 'textInput_cacheRead', rate: 1.25, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 5, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 25, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    releasedAt: '2025-04-03',
-    settings: {
-      searchImpl: 'params',
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -208,52 +185,6 @@ const xaiChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    abilities: {
-      functionCall: true,
-      reasoning: true,
-      search: true,
-    },
-    contextWindowTokens: 131_072,
-    description:
-      '轻量级模型，回话前会先思考。运行快速、智能，适用于不需要深层领域知识的逻辑任务，并能获取原始的思维轨迹。',
-    displayName: 'Grok 3 Mini (Fast mode)',
-    id: 'grok-3-mini-fast', // legacy
-    pricing: {
-      units: [
-        { name: 'textInput_cacheRead', rate: 0.15, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    releasedAt: '2025-04-03',
-    settings: {
-      extendParams: ['reasoningEffort'],
-      searchImpl: 'params',
-    },
-    type: 'chat',
-  },
-  {
-    abilities: {
-      functionCall: true,
-      search: true,
-    },
-    contextWindowTokens: 131_072,
-    description: '该模型在准确性、指令遵循和多语言能力方面有所改进。',
-    displayName: 'Grok 2 1212',
-    id: 'grok-2-1212', // legacy
-    pricing: {
-      units: [
-        { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    releasedAt: '2024-12-12',
-    settings: {
-      searchImpl: 'params',
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,

package/packages/model-bank/src/const/modelProvider.ts

@@ -10,6 +10,7 @@ export enum ModelProvider {
   Baichuan = 'baichuan',
   Bedrock = 'bedrock',
   Bfl = 'bfl',
+  Cerebras = 'cerebras',
   Cloudflare = 'cloudflare',
   Cohere = 'cohere',
   CometAPI = 'cometapi',

package/packages/model-runtime/src/index.ts

@@ -10,6 +10,7 @@ export { LobeAzureAI } from './providers/azureai';
 export { LobeAzureOpenAI } from './providers/azureOpenai';
 export { LobeBedrockAI } from './providers/bedrock';
 export { LobeBflAI } from './providers/bfl';
+export { LobeCerebrasAI } from './providers/cerebras';
 export { LobeCometAPIAI } from './providers/cometapi';
 export { LobeDeepSeekAI } from './providers/deepseek';
 export { LobeGoogleAI } from './providers/google';

package/packages/model-runtime/src/providers/cerebras/index.ts

@@ -0,0 +1,41 @@
+import { ModelProvider } from 'model-bank';
+
+import { createOpenAICompatibleRuntime } from '../../core/openaiCompatibleFactory';
+import { processMultiProviderModelList } from '../../utils/modelParse';
+
+export const LobeCerebrasAI = createOpenAICompatibleRuntime({
+  baseURL: 'https://api.cerebras.ai/v1',
+  chatCompletion: {
+    handlePayload: (payload) => {
+      // eslint-disable-next-line @typescript-eslint/no-unused-vars, unused-imports/no-unused-vars
+      const { frequency_penalty, presence_penalty, model, ...rest } = payload;
+
+      return {
+        ...rest,
+        model,
+      } as any;
+    },
+  },
+  debug: {
+    chatCompletion: () => process.env.DEBUG_CEREBRAS_CHAT_COMPLETION === '1',
+  },
+  models: async ({ client }) => {
+    try {
+      const modelsPage = (await client.models.list()) as any;
+      const modelList = Array.isArray(modelsPage?.data)
+        ? modelsPage.data
+        : Array.isArray(modelsPage)
+          ? modelsPage
+          : [];
+
+      return await processMultiProviderModelList(modelList, 'cerebras');
+    } catch (error) {
+      console.warn(
+        'Failed to fetch Cerebras models. Please ensure your Cerebras API key is valid:',
+        error,
+      );
+      return [];
+    }
+  },
+  provider: ModelProvider.Cerebras,
+});

package/packages/model-runtime/src/runtimeMap.ts

@@ -9,6 +9,7 @@ import { LobeAzureAI } from './providers/azureai';
 import { LobeBaichuanAI } from './providers/baichuan';
 import { LobeBedrockAI } from './providers/bedrock';
 import { LobeBflAI } from './providers/bfl';
+import { LobeCerebrasAI } from './providers/cerebras';
 import { LobeCloudflareAI } from './providers/cloudflare';
 import { LobeCohereAI } from './providers/cohere';
 import { LobeCometAPIAI } from './providers/cometapi';
@@ -74,6 +75,7 @@ export const providerRuntimeMap = {
   baichuan: LobeBaichuanAI,
   bedrock: LobeBedrockAI,
   bfl: LobeBflAI,
+  cerebras: LobeCerebrasAI,
   cloudflare: LobeCloudflareAI,
   cohere: LobeCohereAI,
   cometapi: LobeCometAPIAI,

package/packages/types/src/user/settings/keyVaults.ts

@@ -48,6 +48,7 @@ export interface UserKeyVaults extends SearchEngineKeyVaults {
   baichuan?: OpenAICompatibleKeyVault;
   bedrock?: AWSBedrockKeyVault;
   bfl?: any;
+  cerebras?: OpenAICompatibleKeyVault;
   cloudflare?: CloudflareKeyVault;
   cohere?: OpenAICompatibleKeyVault;
   cometapi?: OpenAICompatibleKeyVault;

package/src/config/modelProviders/cerebras.ts

@@ -0,0 +1,18 @@
+import { ModelProviderCard } from '@/types/llm';
+
+const Cerebras: ModelProviderCard = {
+  chatModels: [],
+  checkModel: 'llama3.1-8b',
+  description:
+    'Cerebras 是一个基于其专用 CS-3 系统的 AI 推理平台，旨在提供全球最快、实时响应、高吞吐量的 LLM 服务，专为消除延迟和加速复杂的 AI 工作流（如实时代码生成和代理任务）而设计。',
+  id: 'cerebras',
+  modelsUrl: 'https://inference-docs.cerebras.ai/models/overview',
+  name: 'Cerebras',
+  settings: {
+    sdkType: 'openai',
+    showModelFetcher: true,
+  },
+  url: 'https://cerebras.ai',
+};
+
+export default Cerebras;

package/src/config/modelProviders/index.ts

@@ -11,6 +11,7 @@ import AzureAIProvider from './azureai';
 import BaichuanProvider from './baichuan';
 import BedrockProvider from './bedrock';
 import BflProvider from './bfl';
+import CerebrasProvider from './cerebras';
 import CloudflareProvider from './cloudflare';
 import CohereProvider from './cohere';
 import CometAPIProvider from './cometapi';
@@ -186,6 +187,7 @@ export const DEFAULT_MODEL_PROVIDER_LIST = [
   NebiusProvider,
   CometAPIProvider,
   VercelAIGatewayProvider,
+  CerebrasProvider,
 ];
 
 export const filterEnabledModels = (provider: ModelProviderCard) => {
@@ -208,6 +210,7 @@ export { default as AzureAIProviderCard } from './azureai';
 export { default as BaichuanProviderCard } from './baichuan';
 export { default as BedrockProviderCard } from './bedrock';
 export { default as BflProviderCard } from './bfl';
+export { default as CerebrasProviderCard } from './cerebras';
 export { default as CloudflareProviderCard } from './cloudflare';
 export { default as CohereProviderCard } from './cohere';
 export { default as CometAPIProviderCard } from './cometapi';

package/src/envs/llm.ts

@@ -198,6 +198,9 @@ export const getLLMConfig = () => {
       ENABLED_NEWAPI: z.boolean(),
       NEWAPI_API_KEY: z.string().optional(),
       NEWAPI_PROXY_URL: z.string().optional(),
+
+      ENABLED_CEREBRAS: z.boolean(),
+      CEREBRAS_API_KEY: z.string().optional(),
     },
     runtimeEnv: {
       API_KEY_SELECT_MODE: process.env.API_KEY_SELECT_MODE,
@@ -394,6 +397,9 @@ export const getLLMConfig = () => {
 
       ENABLED_NEBIUS: !!process.env.NEBIUS_API_KEY,
       NEBIUS_API_KEY: process.env.NEBIUS_API_KEY,
+
+      ENABLED_CEREBRAS: !!process.env.CEREBRAS_API_KEY,
+      CEREBRAS_API_KEY: process.env.CEREBRAS_API_KEY,
     },
   });
 };

package/src/features/PluginsUI/Render/StandaloneType/index.tsx

@@ -20,7 +20,8 @@ const PluginDefaultType = memo<PluginStandaloneTypeProps>(({ payload, id, name =
   const ui = manifest.ui;
 
   if (!ui.url) return;
-
+  // if the id start with "tmp", return directly to avoid duplicate rendering
+  if (id.startsWith('tmp')) return;
   return (
     <IFrameRender
       height={ui.height}