💄 style: Add Claude Haiku 4.5 model (#9735)

* feat: 添加 Claude Haiku 4.5 模型及其相关配置

* fix: 修复模型 ID 格式并移除 Llama 4 Maverick 模型

* 添加 doubao-seed-1.6-lite；更新模型价格区间格式，调整价格单位为百万 tokens

* fix: Invalid combination of reasoning_effort and thinking type: low + disabled

* feat: 添加 Qwen3 VL Flash 和 Qwen3 Coder 30B A3B 模型，更新定价和发布信息

packages/const/src/models.ts

@@ -41,6 +41,7 @@ export const responsesAPIModels = new Set([
  * models support context caching
  */
 export const contextCachingModels = new Set([
+  'claude-haiku-4-5-20251001',
   'claude-sonnet-4-5-latest',
   'claude-sonnet-4-5-20250929',
   'anthropic/claude-sonnet-4.5',
@@ -64,6 +65,7 @@ export const thinkingWithToolClaudeModels = new Set([
   'claude-sonnet-4-20250514',
   'claude-sonnet-4-5-latest',
   'claude-sonnet-4-5-20250929',
+  'claude-haiku-4-5-20251001',
   'anthropic/claude-sonnet-4.5',
   'claude-3-7-sonnet-latest',
   'claude-3-7-sonnet-20250219',

packages/model-bank/src/aiModels/aihubmix.ts

@@ -654,6 +654,40 @@ const aihubmixModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      search: true,
+      structuredOutput: true,
+      vision: true,
+    },
+    contextWindowTokens: 200_000,
+    description: 'Claude Haiku 4.5 是 Anthropic 最快且最智能的 Haiku 模型，具有闪电般的速度和扩展思考能力。',
+    displayName: 'Claude Haiku 4.5',
+    enabled: true,
+    id: 'claude-haiku-4-5-20251001',
+    maxOutput: 64_000,
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 5, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput_cacheRead', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: { prices: { '1h': 2, '5m': 1.25 }, pricingParams: ['ttl'] },
+          name: 'textInput_cacheWrite',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-10-16',
+    settings: {
+      extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'],
+      searchImpl: 'params',
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,

packages/model-bank/src/aiModels/anthropic.ts

@@ -30,6 +30,40 @@ const anthropicChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      search: true,
+      structuredOutput: true,
+      vision: true,
+    },
+    contextWindowTokens: 200_000,
+    description: 'Claude Haiku 4.5 是 Anthropic 最快且最智能的 Haiku 模型，具有闪电般的速度和扩展思考能力。',
+    displayName: 'Claude Haiku 4.5',
+    enabled: true,
+    id: 'claude-haiku-4-5-20251001',
+    maxOutput: 64_000,
+    pricing: {
+      units: [
+        { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 5, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput_cacheRead', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: { prices: { '1h': 2, '5m': 1.25 }, pricingParams: ['ttl'] },
+          name: 'textInput_cacheWrite',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-10-16',
+    settings: {
+      extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'],
+      searchImpl: 'params',
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,

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

@@ -17,23 +17,6 @@ const cerebrasModels: AIChatModelCard[] = [
     },
     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,

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

@@ -11,7 +11,7 @@ const ollamaCloudModels: AIChatModelCard[] = [
       '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',
+    id: 'glm-4.6',
     type: 'chat',
   },
   {

packages/model-bank/src/aiModels/qwen.ts

@@ -5,8 +5,8 @@ import { AIChatModelCard, AIImageModelCard } from '../types/aiModel';
 const qwenChatModels: AIChatModelCard[] = [
   {
     abilities: {
-      vision: true,
       reasoning: true,
+      vision: true,
     },
     config: {
       deploymentName: 'qwen3-vl-plus',
@@ -24,9 +24,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 1,
-              '[32_000, 128_000]': 1.5,
-              '[128_000, infinity]': 3,
+              '[0, 0.032]': 1,
+              '[0.032, 0.128]': 1.5,
+              '[0.128, infinity]': 3,
             },
             pricingParams: ['textInputRange'],
           },
@@ -37,9 +37,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 10,
-              '[32_000, 128_000]': 15,
-              '[128_000, infinity]': 30,
+              '[0, 0.032]': 10,
+              '[0.032, 0.128]': 15,
+              '[0.128, infinity]': 30,
             },
             pricingParams: ['textInputRange'],
           },
@@ -55,12 +55,64 @@ const qwenChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
+  {
+    abilities: {
+      reasoning: true,
+      vision: true,
+    },
+    config: {
+      deploymentName: 'qwen3-vl-flash-2025-10-15',
+    },
+    contextWindowTokens: 262_144,
+    description: 'Qwen3 VL Flash：轻量化高速推理版本，适合对延迟敏感或大批量请求场景。',
+    displayName: 'Qwen3 VL Flash',
+    id: 'qwen3-vl-flash',
+    maxOutput: 32_768,
+    organization: 'Qwen',
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 0.15,
+              '[0.032, 0.128]': 0.3,
+              '[0.128, 0.256]': 0.6,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 1.5,
+              '[0.032, 0.128]': 3,
+              '[0.128, 0.256]': 6,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    releasedAt: '2025-10-15',
+    settings: {
+      extendParams: ['enableReasoning', 'reasoningBudgetToken'],
+    },
+    type: 'chat',
+  },
   {
     abilities: {
       reasoning: true,
     },
     contextWindowTokens: 131_072,
-    description: 'deepseek-v3.2-exp 引入稀疏注意力机制，旨在提升处理长文本时的训练与推理效率，价格低于 deepseek-v3.1。',
+    description:
+      'deepseek-v3.2-exp 引入稀疏注意力机制，旨在提升处理长文本时的训练与推理效率，价格低于 deepseek-v3.1。',
     displayName: 'DeepSeek V3.2 Exp',
     id: 'deepseek-v3.2-exp',
     maxOutput: 65_536,
@@ -136,8 +188,8 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 3,
-              '[32_000, infinity]': 4,
+              '[0, 0.032]': 3,
+              '[0.032, infinity]': 4,
             },
             pricingParams: ['textInputRange'],
           },
@@ -148,8 +200,8 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 14,
-              '[32_000, infinity]': 16,
+              '[0, 0.032]': 14,
+              '[0.032, infinity]': 16,
             },
             pricingParams: ['textInputRange'],
           },
@@ -179,8 +231,8 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[32_000, infinity]': 1.2,
+              '[0, 0.032]': 0.8,
+              '[0.032, infinity]': 1.2,
             },
             pricingParams: ['textInputRange'],
           },
@@ -191,8 +243,8 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 6,
-              '[32_000, infinity]': 8,
+              '[0, 0.032]': 6,
+              '[0.032, infinity]': 8,
             },
             pricingParams: ['textInputRange'],
           },
@@ -212,7 +264,7 @@ const qwenChatModels: AIChatModelCard[] = [
       functionCall: true,
     },
     config: {
-      deploymentName: 'qwen3-coder-plus', // 其支持上下文缓存
+      deploymentName: 'qwen3-coder-plus', // 支持上下文缓存
     },
     contextWindowTokens: 1_000_000,
     description:
@@ -227,10 +279,10 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[32_000, 128_000]': 1.2,
-              '[128_000, 256_000]': 2,
-              '[256_000, infinity]': 4,
+              '[0, 0.032]': 4 * 0.2,
+              '[0.032, 0.128]': 6 * 0.2,
+              '[0.128, 0.256]': 10 * 0.2,
+              '[0.256, infinity]': 20 * 0.2,
             },
             pricingParams: ['textInputRange'],
           },
@@ -241,10 +293,10 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 4,
-              '[32_000, 128_000]': 6,
-              '[128_000, 256_000]': 10,
-              '[256_000, infinity]': 20,
+              '[0, 0.032]': 4,
+              '[0.032, 0.128]': 6,
+              '[0.128, 0.256]': 10,
+              '[0.256, infinity]': 20,
             },
             pricingParams: ['textInputRange'],
           },
@@ -255,10 +307,10 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 16,
-              '[32_000, 128_000]': 24,
-              '[128_000, 256_000]': 40,
-              '[256_000, infinity]': 200,
+              '[0, 0.032]': 16,
+              '[0.032, 0.128]': 24,
+              '[0.128, 0.256]': 40,
+              '[0.256, infinity]': 200,
             },
             pricingParams: ['textInputRange'],
           },
@@ -268,7 +320,6 @@ const qwenChatModels: AIChatModelCard[] = [
         },
       ],
     },
-    releasedAt: '2025-07-22',
     type: 'chat',
   },
   {
@@ -276,7 +327,7 @@ const qwenChatModels: AIChatModelCard[] = [
       functionCall: true,
     },
     config: {
-      deploymentName: 'qwen3-coder-flash',
+      deploymentName: 'qwen3-coder-flash', // 支持上下文缓存
     },
     contextWindowTokens: 1_000_000,
     description:
@@ -288,12 +339,50 @@ const qwenChatModels: AIChatModelCard[] = [
     pricing: {
       currency: 'CNY',
       units: [
-        { name: 'textInput_cacheRead', rate: 1.5 * 0.2, strategy: 'fixed', unit: 'millionTokens' }, // tokens 32K ~ 128K
-        { name: 'textInput', rate: 1.5, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 6, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 0.2,
+              '[0.032, 0.128]': 0.3,
+              '[0.128, 0.256]': 0.5,
+              '[0.256, 1]': 1,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput_cacheRead',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 1,
+              '[0.032, 0.128]': 1.5,
+              '[0.128, 0.256]': 2.5,
+              '[0.256, 1]': 5,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 4,
+              '[0.032, 0.128]': 6,
+              '[0.128, 0.256]': 10,
+              '[0.256, 1]': 25,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
       ],
     },
-    releasedAt: '2025-07-28',
     type: 'chat',
   },
   {
@@ -310,8 +399,76 @@ const qwenChatModels: AIChatModelCard[] = [
     pricing: {
       currency: 'CNY',
       units: [
-        { name: 'textInput', rate: 9, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 36, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 6,
+              '[0.032, 0.128]': 9,
+              '[0.128, 0.2]': 15,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 24,
+              '[0.032, 0.128]': 36,
+              '[0.128, 0.2]': 60,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+      ],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+    },
+    contextWindowTokens: 262_144,
+    description:
+      '通义千问代码模型开源版。最新的 qwen3-coder-30b-a3b-instruct 是基于 Qwen3 的代码生成模型，具有强大的Coding Agent能力，擅长工具调用和环境交互，能够实现自主编程、代码能力卓越的同时兼具通用能力。',
+    displayName: 'Qwen3 Coder 30B A3B',
+    id: 'qwen3-coder-30b-a3b-instruct',
+    maxOutput: 65_536,
+    organization: 'Qwen',
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 1.5,
+              '[0.032, 0.128]': 2.25,
+              '[0.128, 0.2]': 3.75,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 6,
+              '[0.032, 0.128]': 9,
+              '[0.128, 0.2]': 15,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
       ],
     },
     type: 'chat',
@@ -426,7 +583,7 @@ const qwenChatModels: AIChatModelCard[] = [
       currency: 'CNY',
       units: [
         { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' },
       ],
     },
     releasedAt: '2025-09-12',
@@ -450,7 +607,7 @@ const qwenChatModels: AIChatModelCard[] = [
       currency: 'CNY',
       units: [
         { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
       ],
     },
     releasedAt: '2025-09-12',
@@ -663,7 +820,7 @@ const qwenChatModels: AIChatModelCard[] = [
       search: true,
     },
     config: {
-      deploymentName: 'qwq-plus-latest', // expired on 2025-09-02
+      deploymentName: 'qwq-plus-2025-03-05',
     },
     contextWindowTokens: 131_072,
     description:
@@ -679,7 +836,7 @@ const qwenChatModels: AIChatModelCard[] = [
         { name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
       ],
     },
-    releasedAt: '2025-03-06',
+    releasedAt: '2025-03-05',
     settings: {
       searchImpl: 'params',
     },
@@ -796,9 +953,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 128_000]': 0.8 * 0.2,
-              '[128_000, 256_000]': 2.4 * 0.2,
-              '[256_000, infinity]': 4.8 * 0.2,
+              '[0, 0.128]': 0.8 * 0.2,
+              '[0.128, 0.256]': 2.4 * 0.2,
+              '[0.256, infinity]': 4.8 * 0.2,
             },
             pricingParams: ['textInputRange'],
           },
@@ -809,9 +966,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 128_000]': 0.8,
-              '[128_000, 256_000]': 2.4,
-              '[256_000, infinity]': 4.8,
+              '[0, 0.128]': 0.8,
+              '[0.128, 0.256]': 2.4,
+              '[0.256, infinity]': 4.8,
             },
             pricingParams: ['textInputRange'],
           },
@@ -822,12 +979,12 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 128_000]_[false]': 2,
-              '[0, 128_000]_[true]': 8,
-              '[128_000, 256_000]_[false]': 20,
-              '[128_000, 256_000]_[true]': 24,
-              '[256_000, infinity]_[false]': 48,
-              '[256_000, infinity]_[true]': 64,
+              '[0, 0.128]_[false]': 2,
+              '[0, 0.128]_[true]': 8,
+              '[0.128, 0.256]_[false]': 20,
+              '[0.128, 0.256]_[true]': 24,
+              '[0.256, infinity]_[false]': 48,
+              '[0.256, infinity]_[true]': 64,
             },
             pricingParams: ['textInputRange', 'thinkingMode'],
           },
@@ -837,7 +994,6 @@ const qwenChatModels: AIChatModelCard[] = [
         },
       ],
     },
-    releasedAt: '2025-07-14',
     settings: {
       extendParams: ['enableReasoning', 'reasoningBudgetToken'],
       searchImpl: 'params',
@@ -866,9 +1022,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 6 * 0.2,
-              '[32_000, 128_000]': 10 * 0.2,
-              '[128_000, infinity]': 15 * 0.2,
+              '[0, 0.032]': 6 * 0.2,
+              '[0.032, 0.128]': 10 * 0.2,
+              '[0.128, infinity]': 15 * 0.2,
             },
             pricingParams: ['textInputRange'],
           },
@@ -879,9 +1035,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 6,
-              '[32_000, 128_000]': 10,
-              '[128_000, infinity]': 15,
+              '[0, 0.032]': 6,
+              '[0.032, 0.128]': 10,
+              '[0.128, infinity]': 15,
             },
             pricingParams: ['textInputRange'],
           },
@@ -892,9 +1048,9 @@ const qwenChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 24,
-              '[32_000, 128_000]': 40,
-              '[128_000, infinity]': 60,
+              '[0, 0.032]': 24,
+              '[0.032, 0.128]': 40,
+              '[0.128, infinity]': 60,
             },
             pricingParams: ['textInputRange'],
           },
@@ -966,7 +1122,34 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'qwen-omni-turbo-latest', // expired on 2025-08-13
+      deploymentName: 'qwen3-omni-flash-2025-09-15',
+    },
+    contextWindowTokens: 65_536,
+    description:
+      'Qwen-Omni 模型能够接收文本、图片、音频、视频等多种模态的组合输入，并生成文本或语音形式的回复， 提供多种拟人音色，支持多语言和方言的语音输出，可应用于文本创作、视觉识别、语音助手等场景。',
+    displayName: 'Qwen Omni Turbo',
+    id: 'qwen3-omni-flash',
+    maxOutput: 16_384,
+    organization: 'Qwen',
+    pricing: {
+      currency: 'CNY',
+      units: [
+        { name: 'textInput', rate: 1.8, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 6.9, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    releasedAt: '2025-09-15',
+    settings: {
+      extendParams: ['enableReasoning', 'reasoningBudgetToken'],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      vision: true,
+    },
+    config: {
+      deploymentName: 'qwen-omni-turbo-2025-03-26',
     },
     contextWindowTokens: 32_768,
     description:
@@ -1202,7 +1385,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'qvq-max-latest',
+      deploymentName: 'qvq-max-2025-05-15',
     },
     contextWindowTokens: 131_072,
     description:
@@ -1227,7 +1410,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'qvq-plus-latest',
+      deploymentName: 'qvq-plus-2025-05-15',
     },
     contextWindowTokens: 131_072,
     description:
@@ -1687,8 +1870,8 @@ const qwenImageModels: AIImageModelCard[] = [
       seed: { default: null },
     },
     pricing: {
-      currency: 'USD',
-      units: [{ name: 'imageGeneration', rate: 0.041, strategy: 'fixed', unit: 'image' }],
+      currency: 'CNY',
+      units: [{ name: 'imageGeneration', rate: 0.3, strategy: 'fixed', unit: 'image' }],
     },
     releasedAt: '2025-09-18',
     type: 'image',
@@ -1836,7 +2019,7 @@ const qwenImageModels: AIImageModelCard[] = [
     },
     pricing: {
       currency: 'CNY',
-      units: [{ name: 'imageGeneration', rate: 0.04, strategy: 'fixed', unit: 'image' }],
+      units: [{ name: 'imageGeneration', rate: 0.16, strategy: 'fixed', unit: 'image' }],
     },
     releasedAt: '2024-05-22',
     type: 'image',

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

@@ -74,9 +74,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[128_000, infinity]': 4.8,
-              '[32_000, 128_000]': 2.4,
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 2.4,
+              '[0.128, infinity]': 4.8,
             },
             pricingParams: ['textInputRange'],
           },
@@ -87,9 +87,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 8,
-              '[128_000, infinity]': 24,
-              '[32_000, 128_000]': 16,
+              '[0, 0.032]': 8,
+              '[0.032, 0.128]': 16,
+              '[0.128, infinity]': 24,
             },
             pricingParams: ['textInputRange'],
           },
@@ -127,9 +127,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[128_000, infinity]': 2.4,
-              '[32_000, 128_000]': 1.2,
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 1.2,
+              '[0.128, infinity]': 2.4,
             },
             pricingParams: ['textInputRange'],
           },
@@ -140,9 +140,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 8,
-              '[128_000, infinity]': 24,
-              '[32_000, 128_000]': 16,
+              '[0, 0.032]': 8,
+              '[0.032, 0.128]': 16,
+              '[0.128, infinity]': 24,
             },
             pricingParams: ['textInputRange'],
           },
@@ -162,7 +162,7 @@ const doubaoChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'doubao-seed-1-6-250615',
+      deploymentName: 'doubao-seed-1-6-251015',
     },
     contextWindowTokens: 256_000,
     description:
@@ -177,9 +177,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[128_000, infinity]': 2.4,
-              '[32_000, 128_000]': 1.2,
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 1.2,
+              '[0.128, infinity]': 2.4,
             },
             pricingParams: ['textInputRange'],
           },
@@ -190,10 +190,10 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 8192]': 2,
-              '[0, 32_000]_[8192, infinity]': 8,
-              '[128_000, infinity]_[0, infinity]': 24,
-              '[32_000, 128_000]_[0, infinity]': 16,
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 8,
+              '[0.032, 0.128]_[0, infinity]': 16,
+              '[0.128, infinity]_[0, infinity]': 24,
             },
             pricingParams: ['textInputRange', 'textOutputRange'],
           },
@@ -205,7 +205,60 @@ const doubaoChatModels: AIChatModelCard[] = [
       ],
     },
     settings: {
-      extendParams: ['thinking'],
+      extendParams: ['gpt5ReasoningEffort'],
+    },
+    type: 'chat',
+  },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      vision: true,
+    },
+    config: {
+      deploymentName: 'doubao-seed-1-6-lite-251015',
+    },
+    contextWindowTokens: 256_000,
+    description:
+      'Doubao-Seed-1.6-lite 全新多模态深度思考模型，支持思考程度可调节（reasoning effort），即 Minimal、Low、Medium、High 四种模式，更强性价比，常见任务的最佳选择，上下文窗口至256k。',
+    displayName: 'Doubao Seed 1.6 Lite',
+    id: 'doubao-seed-1.6-lite',
+    maxOutput: 32_000,
+    pricing: {
+      currency: 'CNY',
+      units: [
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]': 0.3,
+              '[0.032, 0.128]': 0.6,
+              '[0.128, 0.256]': 1.2,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 0.032]_[0, 0.0002]': 0.6,
+              '[0, 0.032]_[0.0002, infinity]': 2.4,
+              '[0.032, 0.128]_[0, infinity]': 4,
+              '[0.128, 0.256]_[0, infinity]': 12,
+            },
+            pricingParams: ['textInputRange', 'textOutputRange'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        { name: 'textInput_cacheRead', rate: 0.06, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    settings: {
+      extendParams: ['gpt5ReasoningEffort'],
     },
     type: 'chat',
   },
@@ -231,9 +284,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.15,
-              '[128_000, infinity]': 0.6,
-              '[32_000, 128_000]': 0.3,
+              '[0, 0.032]': 0.15,
+              '[0.032, 0.128]': 0.3,
+              '[0.128, infinity]': 0.6,
             },
             pricingParams: ['textInputRange'],
           },
@@ -244,9 +297,9 @@ const doubaoChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 1.5,
-              '[128_000, infinity]': 6,
-              '[32_000, 128_000]': 3,
+              '[0, 0.032]': 1.5,
+              '[0.032, 0.128]': 3,
+              '[0.128, infinity]': 6,
             },
             pricingParams: ['textInputRange'],
           },

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

@@ -23,9 +23,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 0.4,
-              '[0, 32_000]_[200, infinity]': 0.6,
-              '[32_000, 200_000]': 0.8,
+              '[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'],
           },
@@ -36,9 +36,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 2,
-              '[0, 32_000]_[200, infinity]': 3,
-              '[32_000, 200_000]': 4,
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 3,
+              '[0.032, 0.2]': 4,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -49,9 +49,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 8,
-              '[0, 32_000]_[200, infinity]': 14,
-              '[32_000, 200_000]': 16,
+              '[0, 0.032]_[0, 0.0002]': 8,
+              '[0, 0.032]_[0.0002, infinity]': 14,
+              '[0.032, 0.2]': 16,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -87,8 +87,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.4,
-              '[32_000, 65_536]': 0.8,
+              '[0, 0.032]': 0.4,
+              '[0.032, infinity]': 0.8,
             },
             pricingParams: ['textInput'],
           },
@@ -99,8 +99,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 2,
-              '[32_000, 65_536]': 4,
+              '[0, 0.032]': 2,
+              '[0.032, infinity]': 4,
             },
             pricingParams: ['textInput'],
           },
@@ -111,8 +111,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 6,
-              '[32_000, 65_536]': 12,
+              '[0, 0.032]': 6,
+              '[0.032, infinity]': 12,
             },
             pricingParams: ['textInput'],
           },
@@ -146,9 +146,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 0.4,
-              '[0, 32_000]_[200, infinity]': 0.6,
-              '[32_000, 128_000]': 0.8,
+              '[0, 0.032]_[0, 0.0002]': 0.4,
+              '[0, 0.032]_[0.0002, infinity]': 0.6,
+              '[0.032, 0.128]': 0.8,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -159,9 +159,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 2,
-              '[0, 32_000]_[200, infinity]': 3,
-              '[32_000, 128_000]': 4,
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 3,
+              '[0.032, 0.128]': 4,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -172,9 +172,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 8,
-              '[0, 32_000]_[200, infinity]': 14,
-              '[32_000, 128_000]': 16,
+              '[0, 0.032]_[0, 0.0002]': 8,
+              '[0, 0.032]_[0.0002, infinity]': 14,
+              '[0.032, 0.128]': 16,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -207,9 +207,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 1.6,
-              '[0, 32_000]_[200, infinity]': 2.4,
-              '[32_000, 128_000]': 3.2,
+              '[0, 0.032]': 1.6,
+              '[0, 0.032]_[0.0002, infinity]': 2.4,
+              '[0.032, 0.128]': 3.2,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -220,9 +220,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 8,
-              '[0, 32_000]_[200, infinity]': 12,
-              '[32_000, 128_000]': 16,
+              '[0, 0.032]_[0, 0.0002]': 8,
+              '[0, 0.032]_[0.0002, infinity]': 12,
+              '[0.032, 0.128]': 16,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -233,9 +233,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 16,
-              '[0, 32_000]_[200, infinity]': 32,
-              '[32_000, 128_000]': 64,
+              '[0, 0.032]_[0, 0.0002]': 16,
+              '[0, 0.032]_[0.0002, infinity]': 32,
+              '[0.032, 0.128]': 64,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -268,8 +268,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.16,
-              '[32_000, 128_000]': 0.24,
+              '[0, 0.032]': 0.16,
+              '[0.032, 0.128]': 0.24,
             },
             pricingParams: ['textInput'],
           },
@@ -280,8 +280,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[32_000, 128_000]': 1.2,
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 1.2,
             },
             pricingParams: ['textInput'],
           },
@@ -292,9 +292,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 2,
-              '[0, 32_000]_[200, infinity]': 6,
-              '[32_000, 128_000]': 8,
+              '[0, 0.032]_[0, 0.0002]': 2,
+              '[0, 0.032]_[0.0002, infinity]': 6,
+              '[0.032, 0.128]': 8,
             },
             pricingParams: ['textInput', 'textOutput'],
           },
@@ -327,8 +327,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 0.8,
-              '[32_000, 128_000]': 1.6,
+              '[0, 0.032]': 0.8,
+              '[0.032, 0.128]': 1.6,
             },
             pricingParams: ['textInput'],
           },
@@ -339,8 +339,8 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]': 4,
-              '[32_000, 128_000]': 8,
+              '[0, 0.032]': 4,
+              '[0.032, 0.128]': 8,
             },
             pricingParams: ['textInput'],
           },
@@ -351,9 +351,9 @@ const zhipuChatModels: AIChatModelCard[] = [
         {
           lookup: {
             prices: {
-              '[0, 32_000]_[0, 200]': 12,
-              '[0, 32_000]_[200, infinity]': 16,
-              '[32_000, 128_000]': 32,
+              '[0, 0.032]_[0, 0.0002]': 12,
+              '[0, 0.032]_[0.0002, infinity]': 16,
+              '[0.032, 0.128]': 32,
             },
             pricingParams: ['textInput', 'textOutput'],
           },

packages/model-runtime/src/core/parameterResolver.ts

@@ -251,6 +251,7 @@ export const MODEL_PARAMETER_CONFLICTS = {
     'claude-opus-4-1',
     'claude-opus-4-1-20250805',
     'claude-sonnet-4-5-20250929',
+    'claude-haiku-4-5-20251001',
   ]),
 
   /**