💄 style: add llama3.2 model for openrouter provider (#4151)

* Update openrouter.ts * Update index.test.ts.snap * Update openrouter.ts * Update openrouter.ts * Update openrouter.ts * Update openrouter.ts
lobehub · Sep 27, 2024 · 6f1a966 · 6f1a966
1 parent 4619cbf
commit 6f1a966
Show file tree

Hide file tree

Showing 2 changed files with 40 additions and 17 deletions.
diff --git a/src/config/modelProviders/openrouter.ts b/src/config/modelProviders/openrouter.ts
@@ -79,8 +79,10 @@ const OpenRouter: ModelProviderCard = {
       id: 'anthropic/claude-3-haiku',
       maxOutput: 4096,
       pricing: {
+        cachedInput: 0.025,
         input: 0.25,
         output: 1.25,
+        writeCacheInput: 0.3125,
       },
       releasedAt: '2024-03-07',
       tokens: 200_000,
@@ -113,43 +115,41 @@ const OpenRouter: ModelProviderCard = {
       id: 'anthropic/claude-3-opus',
       maxOutput: 4096,
       pricing: {
+        cachedInput: 1.5,
         input: 15,
         output: 75,
+        writeCacheInput: 18.75,
       },
       releasedAt: '2024-02-29',
       tokens: 200_000,
       vision: true,
     },
     {
-      description: 'Gemini 1.5 Flash 0827 提供了优化后的多模态处理能力，适用多种复杂任务场景。',
-      displayName: 'Gemini 1.5 Flash 0827',
+      description: 'Gemini 1.5 Flash 提供了优化后的多模态处理能力，适用多种复杂任务场景。',
+      displayName: 'Gemini 1.5 Flash',
       enabled: true,
       functionCall: true,
-      id: 'google/gemini-flash-1.5-exp',
+      id: 'google/gemini-flash-1.5',
       maxOutput: 8192,
       pricing: {
-        cachedInput: 0.018_75,
         input: 0.075,
         output: 0.3,
       },
-      releasedAt: '2024-08-27',
-      tokens: 1_048_576 + 8192,
+      tokens: 1_000_000 + 8192,
       vision: true,
     },
     {
-      description: 'Gemini 1.5 Pro 0827 结合最新优化技术，带来更高效的多模态数据处理能力。',
-      displayName: 'Gemini 1.5 Pro 0827',
+      description: 'Gemini 1.5 Pro 结合最新优化技术，带来更高效的多模态数据处理能力。',
+      displayName: 'Gemini 1.5 Pro',
       enabled: true,
       functionCall: true,
-      id: 'google/gemini-pro-1.5-exp',
+      id: 'google/gemini-pro-1.5',
       maxOutput: 8192,
       pricing: {
-        cachedInput: 0.875,
         input: 3.5,
         output: 10.5,
       },
-      releasedAt: '2024-08-27',
-      tokens: 2_097_152 + 8192,
+      tokens: 2_000_000 + 8192,
       vision: true,
     },
     {
@@ -160,13 +160,36 @@ const OpenRouter: ModelProviderCard = {
       functionCall: true,
       id: 'deepseek/deepseek-chat',
       pricing: {
-        cachedInput: 0.014,
         input: 0.14,
         output: 0.28,
       },
       releasedAt: '2024-09-05',
       tokens: 128_000,
     },
+    {
+      description: 'LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色，跨越了语言生成和视觉推理之间的鸿沟。',
+      displayName: 'Llama 3.2 11B Vision',
+      enabled: true,
+      id: 'meta-llama/llama-3.2-11b-vision-instruct',
+      pricing: {
+        input: 0.162,
+        output: 0.162,
+      },
+      tokens: 131_072,
+      vision: true,
+    },
+    {
+      description: 'LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色，跨越了语言生成和视觉推理之间的鸿沟。',
+      displayName: 'Llama 3.2 90B Vision',
+      enabled: true,
+      id: 'meta-llama/llama-3.2-90b-vision-instruct',
+      pricing: {
+        input: 0.4,
+        output: 0.4,
+      },
+      tokens: 131_072,
+      vision: true,
+    },
     {
       description: 'Qwen2 是全新的大型语言模型系列，具有更强的理解和生成能力。',
       displayName: 'Qwen2 7B (Free)',

diff --git a/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap b/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap
@@ -83,7 +83,7 @@ Usage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.d
 
 Note: This model is experimental and not suited for production use-cases. It may be removed or redirected to another model in the future.",
     "displayName": "Google: Gemini Flash 1.5 Experimental",
-    "enabled": true,
+    "enabled": false,
     "functionCall": false,
     "id": "google/gemini-flash-1.5-exp",
     "maxTokens": 32768,
@@ -291,7 +291,7 @@ Usage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.d
 
 Note: This model is experimental and not suited for production use-cases. It may be removed or redirected to another model in the future.",
     "displayName": "Google: Gemini Pro 1.5 Experimental",
-    "enabled": true,
+    "enabled": false,
     "functionCall": false,
     "id": "google/gemini-pro-1.5-exp",
     "maxTokens": 32768,
@@ -878,7 +878,7 @@ Usage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.d
 
 #multimodal",
     "displayName": "Google: Gemini Flash 1.5",
-    "enabled": false,
+    "enabled": true,
     "functionCall": false,
     "id": "google/gemini-flash-1.5",
     "maxTokens": 32768,
@@ -1249,7 +1249,7 @@ Usage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.d
 
 #multimodal",
     "displayName": "Google: Gemini Pro 1.5",
-    "enabled": false,
+    "enabled": true,
     "functionCall": false,
     "id": "google/gemini-pro-1.5",
     "maxTokens": 32768,