@lobehub/lobehub 2.0.0-next.186 → 2.0.0-next.187

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

@@ -2,6 +2,66 @@ import { AIChatModelCard, AIImageModelCard } from '../types/aiModel';
 
 // https://siliconflow.cn/zh-cn/models
 const siliconcloudChatModels: AIChatModelCard[] = [
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+    },
+    contextWindowTokens: 200_000,
+    description:
+      'GLM-4.7 是智谱新一代旗舰模型，总参数量 355B，激活参数量 32B，在通用对话、推理和智能体能力方面全面升级。GLM-4.7 增强了 Interleaved Thinking（交错思考），并引入了 Preserved Thinking（保留思考）和 Turn-level Thinking（轮级思考）。',
+    displayName: 'GLM-4.7 (Pro)',
+    id: 'Pro/zai-org/glm-4.7',
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 0.4,
+              '[0, 0.032]_[0.0002, infinity]': 0.6,
+              '[0.032, infinity]_[0, infinity]': 0.8,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textInput_cacheRead',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 3,
+              '[0.032, infinity]_[0, infinity]': 4,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 8,
+              '[0, 0.032]_[0.0002, infinity]': 14,
+              '[0.032, infinity]_[0, infinity]': 16,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-12-22',
+    settings: {
+      extendParams: ['enableReasoning', 'reasoningBudgetToken'],
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,

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

@@ -3,35 +3,6 @@ import { imagenGenParameters, nanoBananaParameters } from './google';
 
 // ref: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models
 const vertexaiChatModels: AIChatModelCard[] = [
-  {
-    abilities: {
-      imageOutput: true,
-      reasoning: true,
-      search: true,
-      vision: true,
-    },
-    contextWindowTokens: 131_072 + 32_768,
-    description:
-      "Gemini 3 Pro Image (Nano Banana Pro) is Google's image generation model and also supports multimodal chat.",
-    displayName: 'Nano Banana Pro',
-    enabled: true,
-    id: 'gemini-3-pro-image-preview',
-    maxOutput: 32_768,
-    pricing: {
-      approximatePricePerImage: 0.134,
-      units: [
-        { name: 'imageOutput', rate: 120, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 12, strategy: 'fixed', unit: 'millionTokens' },
-      ],
-    },
-    releasedAt: '2025-11-20',
-    settings: {
-      searchImpl: 'params',
-      searchProvider: 'google',
-    },
-    type: 'chat',
-  },
   {
     abilities: {
       functionCall: true,
@@ -42,7 +13,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_048_576 + 65_536,
     description:
-      "Gemini 3 Pro is Google’s most powerful agent and vibe-coding model, delivering richer visuals and deeper interaction on top of state-of-the-art reasoning.",
+      'Gemini 3 Pro is Google’s most powerful agent and vibe-coding model, delivering richer visuals and deeper interaction on top of state-of-the-art reasoning.',
     displayName: 'Gemini 3 Pro Preview',
     enabled: true,
     id: 'gemini-3-pro-preview',
@@ -85,6 +56,41 @@ const vertexaiChatModels: AIChatModelCard[] = [
       ],
     },
     releasedAt: '2025-11-18',
+    settings: {
+      extendParams: ['thinkingLevel2', 'urlContext'],
+      searchImpl: 'params',
+      searchProvider: 'google',
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      search: true,
+      video: true,
+      vision: true,
+    },
+    contextWindowTokens: 1_048_576 + 65_536,
+    description: 'Gemini 3 Flash 是为速度而打造的最智能的模型，将前沿智能与卓越的搜索接地相结合。',
+    displayName: 'Gemini 3 Flash Preview',
+    enabled: true,
+    id: 'gemini-3-flash-preview',
+    maxOutput: 65_536,
+    pricing: {
+      units: [
+        { name: 'textInput_cacheRead', rate: 0.05, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 3, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: { prices: { '1h': 1 }, pricingParams: ['ttl'] },
+          name: 'textInput_cacheWrite',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-12-17',
     settings: {
       extendParams: ['thinkingLevel', 'urlContext'],
       searchImpl: 'params',
@@ -92,6 +98,35 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
+  {
+    abilities: {
+      imageOutput: true,
+      reasoning: true,
+      search: true,
+      vision: true,
+    },
+    contextWindowTokens: 131_072 + 32_768,
+    description:
+      'Gemini 3 Pro Image（Nano Banana Pro）是 Google 的图像生成模型，同时支持多模态对话。',
+    displayName: 'Nano Banana Pro',
+    enabled: true,
+    id: 'gemini-3-pro-image-preview',
+    maxOutput: 32_768,
+    pricing: {
+      approximatePricePerImage: 0.134,
+      units: [
+        { name: 'imageOutput', rate: 120, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 12, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    releasedAt: '2025-11-20',
+    settings: {
+      searchImpl: 'params',
+      searchProvider: 'google',
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,
@@ -101,9 +136,8 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_048_576 + 65_536,
     description:
-      "Gemini 2.5 Pro is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.",
+      'Gemini 2.5 Pro is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.',
     displayName: 'Gemini 2.5 Pro',
-    enabled: true,
     id: 'gemini-2.5-pro',
     maxOutput: 65_536,
     pricing: {
@@ -129,7 +163,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_048_576 + 65_536,
     description:
-      "Gemini 2.5 Pro Preview is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.",
+      'Gemini 2.5 Pro Preview is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.',
     displayName: 'Gemini 2.5 Pro Preview 05-06',
     id: 'gemini-2.5-pro-preview-05-06',
     maxOutput: 65_536,
@@ -150,7 +184,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_048_576 + 65_536,
     description:
-      "Gemini 2.5 Pro Preview is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.",
+      'Gemini 2.5 Pro Preview is Google’s most advanced reasoning model, able to reason over code, math, and STEM problems and analyze large datasets, codebases, and documents with long context.',
     displayName: 'Gemini 2.5 Pro Preview 03-25',
     id: 'gemini-2.5-pro-preview-03-25',
     maxOutput: 65_536,
@@ -171,9 +205,8 @@ const vertexaiChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 1_048_576 + 65_536,
-    description: "Gemini 2.5 Flash is Google’s best-value model with full capabilities.",
+    description: 'Gemini 2.5 Flash is Google’s best-value model with full capabilities.',
     displayName: 'Gemini 2.5 Flash',
-    enabled: true,
     id: 'gemini-2.5-flash',
     maxOutput: 65_536,
     pricing: {
@@ -198,7 +231,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 1_048_576 + 65_536,
-    description: "Gemini 2.5 Flash Preview is Google’s best-value model with full capabilities.",
+    description: 'Gemini 2.5 Flash Preview is Google’s best-value model with full capabilities.',
     displayName: 'Gemini 2.5 Flash Preview 04-17',
     id: 'gemini-2.5-flash-preview-04-17',
     maxOutput: 65_536,
@@ -218,7 +251,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 32_768 + 8192,
     description:
-      "Nano Banana is Google’s newest, fastest, and most efficient native multimodal model, enabling conversational image generation and editing.",
+      'Nano Banana is Google’s newest, fastest, and most efficient native multimodal model, enabling conversational image generation and editing.',
     displayName: 'Nano Banana',
     enabled: true,
     id: 'gemini-2.5-flash-image',
@@ -243,7 +276,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_000_000 + 64_000,
     description:
-      "Gemini 2.5 Flash-Lite is Google’s smallest, best-value model, designed for large-scale use.",
+      'Gemini 2.5 Flash-Lite is Google’s smallest, best-value model, designed for large-scale use.',
     displayName: 'Gemini 2.5 Flash-Lite',
     id: 'gemini-2.5-flash-lite',
     maxOutput: 64_000,
@@ -270,7 +303,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_000_000 + 64_000,
     description:
-      "Gemini 2.5 Flash-Lite Preview is Google’s smallest, best-value model, designed for large-scale use.",
+      'Gemini 2.5 Flash-Lite Preview is Google’s smallest, best-value model, designed for large-scale use.',
     displayName: 'Gemini 2.5 Flash-Lite Preview 06-17',
     id: 'gemini-2.5-flash-lite-preview-06-17',
     maxOutput: 64_000,
@@ -315,8 +348,7 @@ const vertexaiChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 1_048_576 + 8192,
-    description:
-      'A Gemini 2.0 Flash variant optimized for cost efficiency and low latency.',
+    description: 'A Gemini 2.0 Flash variant optimized for cost efficiency and low latency.',
     displayName: 'Gemini 2.0 Flash-Lite',
     id: 'gemini-2.0-flash-lite',
     maxOutput: 8192,
@@ -336,7 +368,8 @@ const vertexaiChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 1_000_000 + 8192,
-    description: 'Gemini 1.5 Flash 002 is an efficient multimodal model built for broad deployment.',
+    description:
+      'Gemini 1.5 Flash 002 is an efficient multimodal model built for broad deployment.',
     displayName: 'Gemini 1.5 Flash 002',
     id: 'gemini-1.5-flash-002',
     maxOutput: 8192,
@@ -379,7 +412,7 @@ const vertexaiImageModels: AIImageModelCard[] = [
     enabled: true,
     type: 'image',
     description:
-      "Nano Banana is Google’s newest, fastest, and most efficient native multimodal model, enabling conversational image generation and editing.",
+      'Nano Banana is Google’s newest, fastest, and most efficient native multimodal model, enabling conversational image generation and editing.',
     releasedAt: '2025-08-26',
     parameters: nanoBananaParameters,
     pricing: {

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

@@ -3,6 +3,66 @@ import { AIChatModelCard, AIImageModelCard } from '../types/aiModel';
 // https://www.volcengine.com/docs/82379/1330310
 
 const doubaoChatModels: AIChatModelCard[] = [
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      vision: true,
+    },
+    config: {
+      deploymentName: 'doubao-seed-1-8-251215',
+    },
+    contextWindowTokens: 256_000,
+    description:
+      'Doubao-Seed-1.8 有着更强的多模态理解能力和 Agent 能力，支持文本/图片/视频输入与上下文缓存，可在复杂任务中提供更出色的表现。',
+    displayName: 'Doubao Seed 1.8',
+    id: 'doubao-seed-1.8',
+    maxOutput: 64_000,
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 1.2,
+              '[0.128, 0.256]': 2.4,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 8,
+              '[0.032, 0.128]_[0, infinity]': 16,
+              '[0.128, 0.256]_[0, infinity]': 24,
+            },
+            pricingParams: ['textInputRange', 'textOutputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        { name: 'textInput_cacheRead', rate: 0.16, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: { prices: { '1h': 0.017 }, pricingParams: ['ttl'] },
+          name: 'textInput_cacheWrite',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-12-18',
+    settings: {
+      extendParams: ['gpt5ReasoningEffort'],
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,
@@ -56,6 +116,57 @@ const doubaoChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+    },
+    config: {
+      deploymentName: 'deepseek-v3-2-251201',
+    },
+    contextWindowTokens: 131_072,
+    description:
+      'DeepSeek-V3.2 是深度求索推出的首个将思考融入工具使用的混合推理模型，用高效架构省算力、大规模强化学习提能力、大规模合成任务数据强泛化，三者结合性能媲美 GPT-5-High，输出长度大幅降低，显著减少了计算开销与用户等待时间。',
+    displayName: 'DeepSeek V3.2',
+    enabled: true,
+    id: 'deepseek-v3.2',
+    maxOutput: 32_768,
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 2,
+              '[0.032, 0.128]': 4,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 3,
+              '[0.032, 0.128]': 6,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        { name: 'textInput_cacheRead', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput_cacheWrite', rate: 0.017, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    settings: {
+      extendParams: ['enableReasoning'],
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,
@@ -171,7 +282,6 @@ const doubaoChatModels: AIChatModelCard[] = [
     description:
       'Doubao-Seed-1.6-thinking significantly strengthens reasoning, further improving core abilities in coding, math, and logical reasoning over Doubao-1.5-thinking-pro, while adding vision understanding. It supports a 256k context window and up to 16k output tokens.',
     displayName: 'Doubao Seed 1.6 Thinking',
-    enabled: true,
     id: 'doubao-seed-1.6-thinking',
     maxOutput: 32_000,
     pricing: {
@@ -221,7 +331,6 @@ const doubaoChatModels: AIChatModelCard[] = [
     description:
       'Doubao-Seed-1.6 is a new multimodal deep-reasoning model with auto, thinking, and non-thinking modes. In non-thinking mode, it significantly outperforms Doubao-1.5-pro/250115. It supports a 256k context window and up to 16k output tokens.',
     displayName: 'Doubao Seed 1.6',
-    enabled: true,
     id: 'doubao-seed-1.6',
     maxOutput: 32_000,
     pricing: {

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

@@ -32,7 +32,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     releasedAt: '2025-12-11',
     settings: {
-      extendParams: ['gpt5_1ReasoningEffort', 'textVerbosity'],
+      extendParams: ['gpt5_2ReasoningEffort', 'textVerbosity'],
       searchImpl: 'params',
     },
     type: 'chat',
@@ -147,6 +147,11 @@ const zenmuxChatModels: AIChatModelCard[] = [
       ],
     },
     releasedAt: '2025-11-20',
+    settings: {
+      extendParams: ['thinkingLevel2', 'urlContext'],
+      searchImpl: 'params',
+      searchProvider: 'google',
+    },
     type: 'chat',
   },
   {
@@ -170,7 +175,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
       ],
     },
     settings: {
-      extendParams: ['thinkingLevel', 'urlContext'],
+      extendParams: ['thinkingLevel2', 'urlContext'],
       searchImpl: 'params',
       searchProvider: 'google',
     },
@@ -348,7 +353,8 @@ const zenmuxChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 256_000,
-    description: "Grok 4 is xAI's flagship reasoning model with strong reasoning and multimodal capability.",
+    description:
+      "Grok 4 is xAI's flagship reasoning model with strong reasoning and multimodal capability.",
     displayName: 'Grok 4',
     id: 'x-ai/grok-4',
     maxOutput: 256_000,
@@ -707,7 +713,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_050_000,
     description:
-      "Gemini 2.5 Pro is Google’s flagship reasoning model with long context support for complex tasks.",
+      'Gemini 2.5 Pro is Google’s flagship reasoning model with long context support for complex tasks.',
     displayName: 'Gemini 2.5 Pro',
     id: 'google/gemini-2.5-pro',
     maxOutput: 65_530,
@@ -759,7 +765,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 1_050_000,
     description:
-      "Gemini 2.5 Flash (Lite/Pro/Flash) is Google’s family spanning low latency to high-performance reasoning.",
+      'Gemini 2.5 Flash (Lite/Pro/Flash) is Google’s family spanning low latency to high-performance reasoning.',
     displayName: 'Gemini 2.5 Flash',
     id: 'google/gemini-2.5-flash',
     maxOutput: 65_530,
@@ -931,8 +937,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 1_050_000,
-    description:
-      'GPT-4.1 Mini offers lower latency and better value for mid-context workloads.',
+    description: 'GPT-4.1 Mini offers lower latency and better value for mid-context workloads.',
     displayName: 'GPT-4.1 Mini',
     id: 'openai/gpt-4.1-mini',
     maxOutput: 32_770,
@@ -1076,7 +1081,8 @@ const zenmuxChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 200_000,
-    description: "GLM 4.6 is Z.AI's flagship model with extended context length and coding capability.",
+    description:
+      "GLM 4.6 is Z.AI's flagship model with extended context length and coding capability.",
     displayName: 'GLM 4.6',
     id: 'z-ai/glm-4.6',
     maxOutput: 128_000,
@@ -1125,7 +1131,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 200_000,
     description:
-      "Opus 4.1 is Anthropic’s high-end model optimized for programming, complex reasoning, and long-running tasks.",
+      'Opus 4.1 is Anthropic’s high-end model optimized for programming, complex reasoning, and long-running tasks.',
     displayName: 'Claude Opus 4.1',
     id: 'anthropic/claude-opus-4.1',
     maxOutput: 32_000,
@@ -1150,7 +1156,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 200_000,
     description:
-      "Opus 4 is Anthropic’s flagship model designed for complex tasks and enterprise applications.",
+      'Opus 4 is Anthropic’s flagship model designed for complex tasks and enterprise applications.',
     displayName: 'Claude Opus 4',
     id: 'anthropic/claude-opus-4',
     maxOutput: 32_000,
@@ -1218,7 +1224,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 200_000,
     description:
-      "Claude Sonnet 4.5 is Anthropic’s latest hybrid reasoning model optimized for complex reasoning and coding.",
+      'Claude Sonnet 4.5 is Anthropic’s latest hybrid reasoning model optimized for complex reasoning and coding.',
     displayName: 'Claude Sonnet 4.5',
     id: 'anthropic/claude-sonnet-4.5',
     maxOutput: 64_000,
@@ -1259,7 +1265,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 200_000,
-    description: "OpenAI o4-mini is a small, efficient reasoning model for low-latency scenarios.",
+    description: 'OpenAI o4-mini is a small, efficient reasoning model for low-latency scenarios.',
     displayName: 'o4 Mini',
     id: 'openai/o4-mini',
     maxOutput: 100_000,
@@ -1542,7 +1548,7 @@ const zenmuxChatModels: AIChatModelCard[] = [
     abilities: { reasoning: true },
     contextWindowTokens: 128_000,
     description:
-      "GLM 4.5 is Z.AI’s flagship model with hybrid reasoning optimized for engineering and long-context tasks.",
+      'GLM 4.5 is Z.AI’s flagship model with hybrid reasoning optimized for engineering and long-context tasks.',
     displayName: 'GLM 4.5',
     id: 'z-ai/glm-4.5',
     maxOutput: 96_000,

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

@@ -12,9 +12,71 @@ const zhipuChatModels: AIChatModelCard[] = [
     },
     contextWindowTokens: 200_000,
     description:
-      'Zhipu’s latest flagship GLM-4.6 (355B) surpasses the prior generation in advanced coding, long-context handling, reasoning, and agent capabilities. Its coding performance is on par with Claude Sonnet 4, making it a top-tier coding model in China.',
-    displayName: 'GLM-4.6',
+      'GLM-4.7 是智谱最新旗舰模型，面向 Agentic Coding 场景强化了编码能力、长程任务规划与工具协同，并在多个公开基准的当期榜单中取得开源模型中的领先表现。通用能力提升，回复更简洁自然，写作更具沉浸感。在执行复杂智能体任务，在工具调用时指令遵循更强，Artifacts 与 Agentic Coding 的前端美感和长程任务完成效率进一步提升。',
+    displayName: 'GLM-4.7',
     enabled: true,
+    id: 'glm-4.7',
+    maxOutput: 131_072,
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 0.4,
+              '[0, 0.032]_[0.0002, infinity]': 0.6,
+              '[0.032, 0.2]': 0.8,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textInput_cacheRead',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 3,
+              '[0.032, 0.2]': 4,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 8,
+              '[0, 0.032]_[0.0002, infinity]': 14,
+              '[0.032, 0.2]': 16,
+            },
+            pricingParams: ['textInput', 'textOutput'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    settings: {
+      extendParams: ['enableReasoning'],
+      searchImpl: 'params',
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      search: 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',
     id: 'glm-4.6',
     maxOutput: 131_072,
     pricing: {

package/packages/model-bank/src/types/aiModel.ts

@@ -239,10 +239,13 @@ export type ExtendParamsType =
   | 'reasoningEffort'
   | 'gpt5ReasoningEffort'
   | 'gpt5_1ReasoningEffort'
+  | 'gpt5_2ReasoningEffort'
+  | 'gpt5_2ProReasoningEffort'
   | 'textVerbosity'
   | 'thinking'
   | 'thinkingBudget'
   | 'thinkingLevel'
+  | 'thinkingLevel2'
   | 'imageAspectRatio'
   | 'imageResolution'
   | 'urlContext';

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

@@ -7,12 +7,13 @@ export const LobeVolcengineAI = createOpenAICompatibleRuntime({
   baseURL: 'https://ark.cn-beijing.volces.com/api/v3',
   chatCompletion: {
     handlePayload: (payload) => {
-      const { model, thinking, ...rest } = payload;
+      const { model, thinking, reasoning_effort, ...rest } = payload;
 
       return {
         ...rest,
         model,
         ...(thinking?.type && { thinking: { type: thinking.type } }),
+        ...(reasoning_effort && { reasoning_effort }),
       } as any;
     },
   },