From c5ccd725849ca1370bb2bc7f49326f65230802b4 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Sun, 16 Feb 2025 15:47:13 +0800 Subject: [PATCH 01/20] Update stepfun.ts --- src/config/aiModels/stepfun.ts | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/src/config/aiModels/stepfun.ts b/src/config/aiModels/stepfun.ts index bba33e2bbf1ec..47c635d95e114 100644 --- a/src/config/aiModels/stepfun.ts +++ b/src/config/aiModels/stepfun.ts @@ -198,6 +198,23 @@ const stepfunChatModels: AIChatModelCard[] = [ }, type: 'chat', }, + { + abilities: { + vision: true, + }, + contextWindowTokens: 32_000, + description: '该模型拥有强大的图像理解能力，在数理、代码领域强于1o。模型比1o更小，输出速度更快。', + displayName: 'Step 1o Turbo Vision', + enabled: true, + id: 'step-1o-turbo-vision', + pricing: { + currency: 'CNY', + input: 8, + output: 35, + }, + releasedAt: '2025-02-14', + type: 'chat', + }, ]; export const allModels = [...stepfunChatModels]; From bc6b9ee29aeac4d489a506783367e801974df1c3 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Sun, 16 Feb 2025 15:53:01 +0800 Subject: [PATCH 02/20] Update siliconcloud.ts --- src/config/aiModels/siliconcloud.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/config/aiModels/siliconcloud.ts b/src/config/aiModels/siliconcloud.ts index c2b7dfa4bd31d..3048b150089d0 100644 --- a/src/config/aiModels/siliconcloud.ts +++ b/src/config/aiModels/siliconcloud.ts @@ -28,10 +28,10 @@ const siliconcloudChatModels: AIChatModelCard[] = [ displayName: 'DeepSeek V3', enabled: true, id: 'deepseek-ai/DeepSeek-V3', - pricing: { // 2.9 涨价 + pricing: { currency: 'CNY', - input: 1, - output: 2, + input: 2, + output: 8, }, type: 'chat', }, From 184923d04a4d08f6b20a0cbe29d330e9c55f6180 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Sun, 16 Feb 2025 15:57:36 +0800 Subject: [PATCH 03/20] Update google.ts --- src/config/aiModels/google.ts | 30 ------------------------------ 1 file changed, 30 deletions(-) diff --git a/src/config/aiModels/google.ts b/src/config/aiModels/google.ts index eea45bfe7c0d5..92688a6166467 100644 --- a/src/config/aiModels/google.ts +++ b/src/config/aiModels/google.ts @@ -283,36 +283,6 @@ const googleChatModels: AIChatModelCard[] = [ releasedAt: '2024-09-24', type: 'chat', }, - { - abilities: { - functionCall: true, - }, - contextWindowTokens: 32_768, - description: - 'Gemini 1.0 Pro 001 (Tuning) 提供稳定并可调优的性能，是复杂任务解决方案的理想选择。', - displayName: 'Gemini 1.0 Pro 001 (Tuning)', - id: 'gemini-1.0-pro-001', // Deprecated on 2/15/2025 - maxOutput: 2048, - pricing: { - input: 0.5, - output: 1.5, - }, - releasedAt: '2023-12-06', - type: 'chat', - }, - { - contextWindowTokens: 32_768, - description: 'Gemini 1.0 Pro 002 (Tuning) 提供出色的多模态支持，专注于复杂任务的有效解决。', - displayName: 'Gemini 1.0 Pro 002 (Tuning)', - id: 'gemini-1.0-pro-002', // Deprecated on 2/15/2025 - maxOutput: 2048, - pricing: { - input: 0.5, - output: 1.5, - }, - releasedAt: '2023-12-06', - type: 'chat', - }, ]; export const allModels = [...googleChatModels]; From fb7ea7e50bef8d1d23e0ee91b0a950f9823fc447 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 10:48:20 +0800 Subject: [PATCH 04/20] Update groq.ts --- src/config/aiModels/groq.ts | 209 ++++++++++++++++++------------------ 1 file changed, 106 insertions(+), 103 deletions(-) diff --git a/src/config/aiModels/groq.ts b/src/config/aiModels/groq.ts index 8c23a0fe709e5..86ee9a3b8053d 100644 --- a/src/config/aiModels/groq.ts +++ b/src/config/aiModels/groq.ts @@ -1,66 +1,60 @@ import { AIChatModelCard } from '@/types/aiModel'; +// ref: https://groq.com/pricing/ +// ref: https://console.groq.com/docs/models + const groqChatModels: AIChatModelCard[] = [ { abilities: { + functionCall: true, reasoning: true, }, - contextWindowTokens: 128_000, - description: - 'DeepSeek R1——DeepSeek 套件中更大更智能的模型——被蒸馏到 Llama 70B 架构中。基于基准测试和人工评估，该模型比原始 Llama 70B 更智能，尤其在需要数学和事实精确性的任务上表现出色。', - displayName: 'DeepSeek R1 (Distil-Llama 70B)', - enabled: true, + contextWindowTokens: 131_072, + displayName: 'DeepSeek R1 Distill Llama 70B', id: 'deepseek-r1-distill-llama-70b', + pricing: { + input: 0.75, // 0.75 - 5.00 + output: 0.99, // 0.99 - 5.00 + }, type: 'chat', }, { - abilities: { - functionCall: true, - }, contextWindowTokens: 131_072, - description: - 'Meta Llama 3.3 多语言大语言模型 ( LLM ) 是 70B（文本输入/文本输出）中的预训练和指令调整生成模型。 Llama 3.3 指令调整的纯文本模型针对多语言对话用例进行了优化，并且在常见行业基准上优于许多可用的开源和封闭式聊天模型。', - displayName: 'Llama 3.3 70B', - enabled: true, - id: 'llama-3.3-70b-versatile', - maxOutput: 8192, + displayName: 'DeepSeek R1 Distill Llama 70B SpecDec', + id: 'deepseek-r1-distill-llama-70b-specdec', + maxOutput: 16_384, pricing: { - input: 0.05, - output: 0.08, + input: 0.75, + output: 0.99, }, type: 'chat', }, { abilities: { - vision: true, + functionCall: true, + reasoning: true, }, - contextWindowTokens: 8192, - 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 (Preview)', - enabled: true, - id: 'llama-3.2-11b-vision-preview', - maxOutput: 8192, + contextWindowTokens: 131_072, + displayName: 'DeepSeek R1 Distill Qwen 32B', + id: 'deepseek-r1-distill-qwen-32b', + maxOutput: 16_384, pricing: { - input: 0.05, - output: 0.08, + input: 0.69, + output: 0.69, }, type: 'chat', }, { abilities: { - vision: true, + functionCall: true, }, - contextWindowTokens: 8192, - 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 (Preview)', - enabled: true, - id: 'llama-3.2-90b-vision-preview', - maxOutput: 8192, + contextWindowTokens: 8_192, + description: 'Gemma 2 9B 是一款优化用于特定任务和工具整合的模型。', + displayName: 'Gemma 2 9B', + id: 'gemma2-9b-it', pricing: { - input: 0.59, - output: 0.79, + input: 0.20, + output: 0.20, }, type: 'chat', }, @@ -69,12 +63,10 @@ const groqChatModels: AIChatModelCard[] = [ functionCall: true, }, contextWindowTokens: 131_072, - description: - 'Llama 3.1 8B 是一款高效能模型，提供了快速的文本生成能力，非常适合需要大规模效率和成本效益的应用场景。', - displayName: 'Llama 3.1 8B', - enabled: true, + description: 'Llama 3.1 8B 是一款高效能模型，提供了快速的文本生成能力，非常适合需要大规模效率和成本效益的应用场景。', + displayName: 'Llama 3.1 8B Instant', id: 'llama-3.1-8b-instant', - maxOutput: 8192, + maxOutput: 8_192, pricing: { input: 0.05, output: 0.08, @@ -83,60 +75,63 @@ const groqChatModels: AIChatModelCard[] = [ }, { abilities: { - functionCall: true, + vision: true, }, contextWindowTokens: 131_072, - description: - 'Llama 3.1 70B 提供更强大的AI推理能力，适合复杂应用，支持超多的计算处理并保证高效和准确率。', - displayName: 'Llama 3.1 70B', - enabled: true, - id: 'llama-3.1-70b-versatile', - maxOutput: 8192, + 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 (Preview)', + id: 'llama-3.2-11b-vision-preview', + maxOutput: 8_192, pricing: { - input: 0.59, - output: 0.79, + input: 0.18, + output: 0.18, }, type: 'chat', }, { abilities: { - functionCall: true, + vision: true, }, - contextWindowTokens: 8192, - description: 'Llama 3 Groq 8B Tool Use 是针对高效工具使用优化的模型，支持快速并行计算。', - displayName: 'Llama 3 Groq 8B Tool Use (Preview)', - id: 'llama3-groq-8b-8192-tool-use-preview', + contextWindowTokens: 131_072, + 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 (Preview)', + id: 'llama-3.2-90b-vision-preview', + maxOutput: 8_192, pricing: { - input: 0.19, - output: 0.19, + input: 0.90, + output: 0.90, }, type: 'chat', }, { - abilities: { - functionCall: true, - }, - contextWindowTokens: 8192, - description: 'Llama 3 Groq 70B Tool Use 提供强大的工具调用能力，支持复杂任务的高效处理。', - displayName: 'Llama 3 Groq 70B Tool Use (Preview)', - id: 'llama3-groq-70b-8192-tool-use-preview', + contextWindowTokens: 131_072, + displayName: 'Llama 3.2 1B (Preview)', + id: 'llama-3.2-1b-preview', + maxOutput: 8_192, pricing: { - input: 0.89, - output: 0.89, + input: 0.04, + output: 0.04, }, type: 'chat', }, { - abilities: { - functionCall: true, + contextWindowTokens: 131_072, + displayName: 'Llama 3.2 3B (Preview)', + id: 'llama-3.2-3b-preview', + maxOutput: 8_192, + pricing: { + input: 0.06, + output: 0.06, }, - contextWindowTokens: 8192, - description: 'Meta Llama 3 8B 带来优质的推理效能，适合多场景应用需求。', - displayName: 'Meta Llama 3 8B', - id: 'llama3-8b-8192', + type: 'chat', + }, + { + contextWindowTokens: 8_192, + displayName: 'Llama 3.3 70B SpecDec', + id: 'llama-3.3-70b-specdec', pricing: { - input: 0.05, - output: 0.08, + input: 0.59, + output: 0.99, }, type: 'chat', }, @@ -144,10 +139,11 @@ const groqChatModels: AIChatModelCard[] = [ abilities: { functionCall: true, }, - contextWindowTokens: 8192, - description: 'Meta Llama 3 70B 提供无与伦比的复杂性处理能力，为高要求项目量身定制。', - displayName: 'Meta Llama 3 70B', - id: 'llama3-70b-8192', + contextWindowTokens: 131_072, + description: 'Meta Llama 3.3 多语言大语言模型 ( LLM ) 是 70B（文本输入/文本输出）中的预训练和指令调整生成模型。 Llama 3.3 指令调整的纯文本模型针对多语言对话用例进行了优化，并且在常见行业基准上优于许多可用的开源和封闭式聊天模型。', + displayName: 'Llama 3.3 70B Versatile', + id: 'llama-3.3-70b-versatile', + maxOutput: 32_768, pricing: { input: 0.59, output: 0.79, @@ -155,31 +151,24 @@ const groqChatModels: AIChatModelCard[] = [ type: 'chat', }, { - abilities: { - functionCall: true, - }, - contextWindowTokens: 8192, - description: 'Gemma 2 9B 是一款优化用于特定任务和工具整合的模型。', - displayName: 'Gemma 2 9B', - enabled: true, - id: 'gemma2-9b-it', + contextWindowTokens: 8_192, + description: 'Meta Llama 3 70B 提供无与伦比的复杂性处理能力，为高要求项目量身定制。', + displayName: 'Llama 3 70B', + id: 'llama3-70b-8192', pricing: { - input: 0.2, - output: 0.2, + input: 0.59, + output: 0.79, }, type: 'chat', }, { - abilities: { - functionCall: true, - }, - contextWindowTokens: 8192, - description: 'Gemma 7B 适合中小规模任务处理，兼具成本效益。', - displayName: 'Gemma 7B', - id: 'gemma-7b-it', + contextWindowTokens: 8_192, + description: 'Meta Llama 3 8B 带来优质的推理效能，适合多场景应用需求。', + displayName: 'Llama 3 8B', + id: 'llama3-8b-8192', pricing: { - input: 0.07, - output: 0.07, + input: 0.05, + output: 0.08, }, type: 'chat', }, @@ -189,7 +178,7 @@ const groqChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 32_768, description: 'Mixtral 8x7B 提供高容错的并行计算能力，适合复杂任务。', - displayName: 'Mixtral 8x7B', + displayName: 'Mixtral 8x7B Instruct', id: 'mixtral-8x7b-32768', pricing: { input: 0.24, @@ -199,12 +188,26 @@ const groqChatModels: AIChatModelCard[] = [ }, { abilities: { - vision: true, + functionCall: true, + }, + contextWindowTokens: 131_072, + displayName: 'Qwen 2.5 32B', + id: 'qwen-2.5-32b', + maxOutput: 8_192, + pricing: { + input: 0.79, + output: 0.79, + }, + type: 'chat', + }, + { + contextWindowTokens: 8_192, + displayName: 'Llama Guard 3 8B', + id: 'llama-guard-3-8b', + pricing: { + input: 0.20, + output: 0.20, }, - contextWindowTokens: 4096, - description: 'LLaVA 1.5 7B 提供视觉处理能力融合，通过视觉信息输入生成复杂输出。', - displayName: 'LLaVA 1.5 7B', - id: 'llava-v1.5-7b-4096-preview', type: 'chat', }, ]; From 9290930a295ee407347ae6066f654c9b04245ec7 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 10:49:19 +0800 Subject: [PATCH 05/20] Update siliconcloud.ts --- src/config/aiModels/siliconcloud.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/config/aiModels/siliconcloud.ts b/src/config/aiModels/siliconcloud.ts index 3048b150089d0..6e9f30104a14c 100644 --- a/src/config/aiModels/siliconcloud.ts +++ b/src/config/aiModels/siliconcloud.ts @@ -1,5 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://siliconflow.cn/zh-cn/models + const siliconcloudChatModels: AIChatModelCard[] = [ { abilities: { From 4371403648aef5e47b9d2b01d1ed4ae96b22252f Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 10:49:56 +0800 Subject: [PATCH 06/20] Update stepfun.ts --- src/config/aiModels/stepfun.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/config/aiModels/stepfun.ts b/src/config/aiModels/stepfun.ts index 47c635d95e114..71b40d48d74e8 100644 --- a/src/config/aiModels/stepfun.ts +++ b/src/config/aiModels/stepfun.ts @@ -1,5 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://platform.stepfun.com/docs/pricing/details + const stepfunChatModels: AIChatModelCard[] = [ { abilities: { From 6223ffef28619e55f7e0a6b95b7e8830e7b68a11 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 10:53:11 +0800 Subject: [PATCH 07/20] Update groq.ts --- src/config/aiModels/groq.ts | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/src/config/aiModels/groq.ts b/src/config/aiModels/groq.ts index 86ee9a3b8053d..354c60367d759 100644 --- a/src/config/aiModels/groq.ts +++ b/src/config/aiModels/groq.ts @@ -1,7 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; -// ref: https://groq.com/pricing/ -// ref: https://console.groq.com/docs/models +// https://groq.com/pricing/ +// https://console.groq.com/docs/models const groqChatModels: AIChatModelCard[] = [ { @@ -11,6 +11,7 @@ const groqChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 131_072, displayName: 'DeepSeek R1 Distill Llama 70B', + enabled: true, id: 'deepseek-r1-distill-llama-70b', pricing: { input: 0.75, // 0.75 - 5.00 @@ -36,6 +37,7 @@ const groqChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 131_072, displayName: 'DeepSeek R1 Distill Qwen 32B', + enabled: true, id: 'deepseek-r1-distill-qwen-32b', maxOutput: 16_384, pricing: { @@ -95,6 +97,7 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, 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 (Preview)', + enabled: true, id: 'llama-3.2-90b-vision-preview', maxOutput: 8_192, pricing: { @@ -142,6 +145,7 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, description: 'Meta Llama 3.3 多语言大语言模型 ( LLM ) 是 70B（文本输入/文本输出）中的预训练和指令调整生成模型。 Llama 3.3 指令调整的纯文本模型针对多语言对话用例进行了优化，并且在常见行业基准上优于许多可用的开源和封闭式聊天模型。', displayName: 'Llama 3.3 70B Versatile', + enabled: true, id: 'llama-3.3-70b-versatile', maxOutput: 32_768, pricing: { From 13cc52c963addd224e1a7c065facd597a6864cb9 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 12:17:21 +0800 Subject: [PATCH 08/20] Update groq.ts --- src/config/aiModels/groq.ts | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/src/config/aiModels/groq.ts b/src/config/aiModels/groq.ts index 354c60367d759..35890d2c9d86e 100644 --- a/src/config/aiModels/groq.ts +++ b/src/config/aiModels/groq.ts @@ -50,13 +50,13 @@ const groqChatModels: AIChatModelCard[] = [ abilities: { functionCall: true, }, - contextWindowTokens: 8_192, + contextWindowTokens: 8192, description: 'Gemma 2 9B 是一款优化用于特定任务和工具整合的模型。', displayName: 'Gemma 2 9B', id: 'gemma2-9b-it', pricing: { - input: 0.20, - output: 0.20, + input: 0.2, + output: 0.2, }, type: 'chat', }, @@ -68,7 +68,7 @@ const groqChatModels: AIChatModelCard[] = [ description: 'Llama 3.1 8B 是一款高效能模型，提供了快速的文本生成能力，非常适合需要大规模效率和成本效益的应用场景。', displayName: 'Llama 3.1 8B Instant', id: 'llama-3.1-8b-instant', - maxOutput: 8_192, + maxOutput: 8192, pricing: { input: 0.05, output: 0.08, @@ -83,7 +83,7 @@ const groqChatModels: AIChatModelCard[] = [ 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 (Preview)', id: 'llama-3.2-11b-vision-preview', - maxOutput: 8_192, + maxOutput: 8192, pricing: { input: 0.18, output: 0.18, @@ -99,10 +99,10 @@ const groqChatModels: AIChatModelCard[] = [ displayName: 'Llama 3.2 90B Vision (Preview)', enabled: true, id: 'llama-3.2-90b-vision-preview', - maxOutput: 8_192, + maxOutput: 8192, pricing: { - input: 0.90, - output: 0.90, + input: 0.9, + output: 0.9, }, type: 'chat', }, @@ -110,7 +110,7 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, displayName: 'Llama 3.2 1B (Preview)', id: 'llama-3.2-1b-preview', - maxOutput: 8_192, + maxOutput: 8192, pricing: { input: 0.04, output: 0.04, @@ -121,7 +121,7 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, displayName: 'Llama 3.2 3B (Preview)', id: 'llama-3.2-3b-preview', - maxOutput: 8_192, + maxOutput: 8192, pricing: { input: 0.06, output: 0.06, @@ -129,7 +129,7 @@ const groqChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 8_192, + contextWindowTokens: 8192, displayName: 'Llama 3.3 70B SpecDec', id: 'llama-3.3-70b-specdec', pricing: { @@ -155,7 +155,7 @@ const groqChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 8_192, + contextWindowTokens: 8192, description: 'Meta Llama 3 70B 提供无与伦比的复杂性处理能力，为高要求项目量身定制。', displayName: 'Llama 3 70B', id: 'llama3-70b-8192', @@ -166,7 +166,7 @@ const groqChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 8_192, + contextWindowTokens: 8192, description: 'Meta Llama 3 8B 带来优质的推理效能，适合多场景应用需求。', displayName: 'Llama 3 8B', id: 'llama3-8b-8192', @@ -197,7 +197,7 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, displayName: 'Qwen 2.5 32B', id: 'qwen-2.5-32b', - maxOutput: 8_192, + maxOutput: 8192, pricing: { input: 0.79, output: 0.79, @@ -205,12 +205,12 @@ const groqChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 8_192, + contextWindowTokens: 8192, displayName: 'Llama Guard 3 8B', id: 'llama-guard-3-8b', pricing: { - input: 0.20, - output: 0.20, + input: 0.2, + output: 0.2, }, type: 'chat', }, From 9351d33f4e98fc9d7abd037e19e42f1a27d00e70 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 20:33:23 +0800 Subject: [PATCH 09/20] Update hunyuan.ts --- src/config/aiModels/hunyuan.ts | 38 ++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) diff --git a/src/config/aiModels/hunyuan.ts b/src/config/aiModels/hunyuan.ts index 5e61406079388..fde356289418e 100644 --- a/src/config/aiModels/hunyuan.ts +++ b/src/config/aiModels/hunyuan.ts @@ -30,7 +30,7 @@ const hunyuanChatModels: AIChatModelCard[] = [ input: 0.8, output: 2, }, - releasedAt: '2024-10-28', + releasedAt: '2025-02-10', type: 'chat', }, { @@ -46,7 +46,7 @@ const hunyuanChatModels: AIChatModelCard[] = [ input: 0.5, output: 2, }, - releasedAt: '2024-10-28', + releasedAt: '2025-02-10', type: 'chat', }, { @@ -56,7 +56,7 @@ const hunyuanChatModels: AIChatModelCard[] = [ contextWindowTokens: 32_000, description: '通用体验优化，包括NLP理解、文本创作、闲聊、知识问答、翻译、领域等；提升拟人性，优化模型情商；提升意图模糊时模型主动澄清能力；提升字词解析类问题的处理能力；提升创作的质量和可互动性；提升多轮体验。', - displayName: 'Hunyuan Turbo', + displayName: 'Hunyuan Turbo Latest', enabled: true, id: 'hunyuan-turbo-latest', maxOutput: 4000, @@ -135,7 +135,7 @@ const hunyuanChatModels: AIChatModelCard[] = [ input: 4, output: 12, }, - releasedAt: '2024-11-20', + releasedAt: '2025-02-10', type: 'chat', }, { @@ -264,6 +264,36 @@ const hunyuanChatModels: AIChatModelCard[] = [ releasedAt: '2024-07-04', type: 'chat', }, + { + contextWindowTokens: 8000, + description: + '支持中文和英语、日语、法语、葡萄牙语、西班牙语、土耳其语、俄语、阿拉伯语、韩语、意大利语、德语、越南语、马来语、印尼语15种语言互译，基于多场景翻译评测集自动化评估COMET评分，在十余种常用语种中外互译能力上整体优于市场同规模模型。', + displayName: 'Hunyuan Translation', + id: 'hunyuan-translation', + maxOutput: 4000, + pricing: { + currency: 'CNY', + input: 25, + output: 75, + }, + releasedAt: '2024-10-25', + type: 'chat', + }, + { + contextWindowTokens: 8000, + description: + '混元翻译模型支持自然语言对话式翻译；支持中文和英语、日语、法语、葡萄牙语、西班牙语、土耳其语、俄语、阿拉伯语、韩语、意大利语、德语、越南语、马来语、印尼语15种语言互译。', + displayName: 'Hunyuan Translation Lite', + id: 'hunyuan-translation-lite', + maxOutput: 4000, + pricing: { + currency: 'CNY', + input: 5, + output: 15, + }, + releasedAt: '2024-11-25', + type: 'chat', + }, ]; export const allModels = [...hunyuanChatModels]; From 315f002222ce2aec644da0c9747d4954bb1a0ad3 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 20:33:56 +0800 Subject: [PATCH 10/20] Update hunyuan.ts --- src/config/aiModels/hunyuan.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/config/aiModels/hunyuan.ts b/src/config/aiModels/hunyuan.ts index fde356289418e..6ba991859be4b 100644 --- a/src/config/aiModels/hunyuan.ts +++ b/src/config/aiModels/hunyuan.ts @@ -1,5 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://cloud.tencent.com/document/product/1729/104753 + const hunyuanChatModels: AIChatModelCard[] = [ { contextWindowTokens: 256_000, From e2af88b21d0e682053cac18ce36be9aa1326d936 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 20:47:18 +0800 Subject: [PATCH 11/20] Update internlm.ts --- src/config/aiModels/internlm.ts | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/src/config/aiModels/internlm.ts b/src/config/aiModels/internlm.ts index 776c7eb44ff45..d1e35ad8ea605 100644 --- a/src/config/aiModels/internlm.ts +++ b/src/config/aiModels/internlm.ts @@ -1,5 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://internlm.intern-ai.org.cn/api/document + const internlmChatModels: AIChatModelCard[] = [ { abilities: { @@ -7,11 +9,10 @@ const internlmChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 32_768, description: - '我们最新的模型系列，有着卓越的推理性能，领跑同量级开源模型。默认指向我们最新发布的 InternLM3 系列模型', + '我们最新的模型系列，有着卓越的推理性能，领跑同量级开源模型。默认指向我们最新发布的 InternLM3 系列模型，当前指向 internlm3-8b-instruct。', displayName: 'InternLM3', enabled: true, id: 'internlm3-latest', - maxOutput: 4096, pricing: { input: 0, output: 0, @@ -24,11 +25,10 @@ const internlmChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 32_768, description: - '我们仍在维护的老版本模型，经过多轮迭代有着极其优异且稳定的性能，包含 7B、20B 多种模型参数量可选，支持 1M 的上下文长度以及更强的指令跟随和工具调用能力。默认指向我们最新发布的 InternLM2.5 系列模型', + '我们仍在维护的老版本模型，经过多轮迭代有着极其优异且稳定的性能，包含 7B、20B 多种模型参数量可选，支持 1M 的上下文长度以及更强的指令跟随和工具调用能力。默认指向我们最新发布的 InternLM2.5 系列模型，当前指向 internlm2.5-20b-chat。', displayName: 'InternLM2.5', enabled: true, id: 'internlm2.5-latest', - maxOutput: 4096, pricing: { input: 0, output: 0, @@ -43,7 +43,6 @@ const internlmChatModels: AIChatModelCard[] = [ description: 'InternLM2 版本最大的模型，专注于高度复杂的任务', displayName: 'InternLM2 Pro Chat', id: 'internlm2-pro-chat', - maxOutput: 4096, pricing: { input: 0, output: 0, From 14ecf4c127b84b9f9269b2110267ccee2a920fca Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 21:17:27 +0800 Subject: [PATCH 12/20] Update mistral.ts --- src/config/aiModels/mistral.ts | 56 +++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 21 deletions(-) diff --git a/src/config/aiModels/mistral.ts b/src/config/aiModels/mistral.ts index 03badd0caa152..e5b2d858bd056 100644 --- a/src/config/aiModels/mistral.ts +++ b/src/config/aiModels/mistral.ts @@ -1,5 +1,8 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://docs.mistral.ai/getting-started/models/models_overview/ +// https://mistral.ai/products/la-plateforme#pricing + const mistralChatModels: AIChatModelCard[] = [ { abilities: { @@ -12,8 +15,8 @@ const mistralChatModels: AIChatModelCard[] = [ enabled: true, id: 'open-mistral-nemo', pricing: { - input: 0.15, - output: 0.15, + input: 0, + output: 0, }, type: 'chat', }, @@ -21,14 +24,14 @@ const mistralChatModels: AIChatModelCard[] = [ abilities: { functionCall: true, }, - contextWindowTokens: 128_000, + contextWindowTokens: 32_000, description: 'Mistral Small是成本效益高、快速且可靠的选项，适用于翻译、摘要和情感分析等用例。', displayName: 'Mistral Small', enabled: true, id: 'mistral-small-latest', pricing: { - input: 0.2, - output: 0.6, + input: 0.1, + output: 0.3, }, type: 'chat', }, @@ -36,7 +39,7 @@ const mistralChatModels: AIChatModelCard[] = [ abilities: { functionCall: true, }, - contextWindowTokens: 128_000, + contextWindowTokens: 131_072, description: 'Mistral Large是旗舰大模型，擅长多语言任务、复杂推理和代码生成，是高端应用的理想选择。', displayName: 'Mistral Large', @@ -49,14 +52,18 @@ const mistralChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 32_768, - description: 'Codestral是专注于代码生成的尖端生成模型，优化了中间填充和代码补全任务。', + abilities: { + functionCall: true, + }, + contextWindowTokens: 256_000, + description: 'Codestral 是我们最先进的编码语言模型，第二个版本于2025年1月发布，专门从事低延迟、高频任务如中间填充（RST）、代码纠正和测试生成。', displayName: 'Codestral', id: 'codestral-latest', pricing: { - input: 0.2, - output: 0.6, + input: 0.3, + output: 0.9, }, + releasedAt: '2025-01-13', type: 'chat', }, { @@ -64,7 +71,7 @@ const mistralChatModels: AIChatModelCard[] = [ functionCall: true, vision: true, }, - contextWindowTokens: 128_000, + contextWindowTokens: 131_072, description: 'Pixtral Large 是一款拥有 1240 亿参数的开源多模态模型，基于 Mistral Large 2 构建。这是我们多模态家族中的第二款模型，展现了前沿水平的图像理解能力。', displayName: 'Pixtral Large', @@ -78,22 +85,26 @@ const mistralChatModels: AIChatModelCard[] = [ }, { abilities: { + functionCall: true, vision: true, }, - contextWindowTokens: 128_000, + contextWindowTokens: 131_072, description: 'Pixtral 模型在图表和图理解、文档问答、多模态推理和指令遵循等任务上表现出强大的能力，能够以自然分辨率和宽高比摄入图像，还能够在长达 128K 令牌的长上下文窗口中处理任意数量的图像。', displayName: 'Pixtral 12B', enabled: true, id: 'pixtral-12b-2409', pricing: { - input: 0.15, - output: 0.15, + input: 0, + output: 0, }, type: 'chat', }, { - contextWindowTokens: 128_000, + abilities: { + functionCall: true, + }, + contextWindowTokens: 131_072, description: 'Ministral 3B 是Mistral的世界顶级边缘模型。', displayName: 'Ministral 3B', id: 'ministral-3b-latest', @@ -104,7 +115,10 @@ const mistralChatModels: AIChatModelCard[] = [ type: 'chat', }, { - contextWindowTokens: 128_000, + abilities: { + functionCall: true, + }, + contextWindowTokens: 131_072, description: 'Ministral 8B 是Mistral的性价比极高的边缘模型。', displayName: 'Ministral 8B', id: 'ministral-8b-latest', @@ -119,7 +133,7 @@ const mistralChatModels: AIChatModelCard[] = [ description: 'Mistral 7B是一款紧凑但高性能的模型，擅长批量处理和简单任务，如分类和文本生成，具有良好的推理能力。', displayName: 'Mistral 7B', - id: 'open-mistral-7b', + id: 'open-mistral-7b', // Deprecated on 2025/03/30 pricing: { input: 0.25, output: 0.25, @@ -131,7 +145,7 @@ const mistralChatModels: AIChatModelCard[] = [ description: 'Mixtral 8x7B是一个稀疏专家模型，利用多个参数提高推理速度，适合处理多语言和代码生成任务。', displayName: 'Mixtral 8x7B', - id: 'open-mixtral-8x7b', + id: 'open-mixtral-8x7b', // Deprecated on 2025/03/30 pricing: { input: 0.7, output: 0.7, @@ -146,7 +160,7 @@ const mistralChatModels: AIChatModelCard[] = [ description: 'Mixtral 8x22B是一个更大的专家模型，专注于复杂任务，提供出色的推理能力和更高的吞吐量。', displayName: 'Mixtral 8x22B', - id: 'open-mixtral-8x22b', + id: 'open-mixtral-8x22b', // Deprecated on 2025/03/30 pricing: { input: 2, output: 6, @@ -160,8 +174,8 @@ const mistralChatModels: AIChatModelCard[] = [ displayName: 'Codestral Mamba', id: 'open-codestral-mamba', pricing: { - input: 0.15, - output: 0.15, + input: 0, + output: 0, }, type: 'chat', }, From 563e0a5f30a2151803d6237335bf8b237c82e38b Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 22:09:21 +0800 Subject: [PATCH 13/20] Update novita.ts --- src/config/aiModels/novita.ts | 325 ++++++++++++++++++++++++++++++---- 1 file changed, 293 insertions(+), 32 deletions(-) diff --git a/src/config/aiModels/novita.ts b/src/config/aiModels/novita.ts index 6c15eb5744201..f0d3b6f7075fc 100644 --- a/src/config/aiModels/novita.ts +++ b/src/config/aiModels/novita.ts @@ -1,31 +1,39 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://novita.ai/pricing + const novitaChatModels: AIChatModelCard[] = [ { - contextWindowTokens: 8192, - description: - 'Llama 3.1 8B Instruct 是 Meta 推出的最新版本，优化了高质量对话场景，表现优于许多领先的闭源模型。', - displayName: 'Llama 3.1 8B Instruct', + contextWindowTokens: 131_072, + displayName: 'Llama 3.3 70B Instruct', enabled: true, - id: 'meta-llama/llama-3.1-8b-instruct', + id: 'meta-llama/llama-3.3-70b-instruct', + pricing: { + input: 0.39, + output: 0.39, + }, type: 'chat', }, { - contextWindowTokens: 131_072, - description: - 'Llama 3.1 70B Instruct 专为高质量对话而设计，在人类评估中表现突出，特别适合高交互场景。', - displayName: 'Llama 3.1 70B Instruct', - enabled: true, - id: 'meta-llama/llama-3.1-70b-instruct', + contextWindowTokens: 16_384, + description: 'Llama 3.1 8B Instruct 是 Meta 推出的最新版本，优化了高质量对话场景，表现优于许多领先的闭源模型。', + displayName: 'Llama 3.1 8B Instruct', + id: 'meta-llama/llama-3.1-8b-instruct', + pricing: { + input: 0.05, + output: 0.05, + }, type: 'chat', }, { contextWindowTokens: 32_768, - description: - 'Llama 3.1 405B Instruct 是 Meta最新推出的版本，优化用于生成高质量对话，超越了许多领导闭源模型。', - displayName: 'Llama 3.1 405B Instruct', - enabled: true, - id: 'meta-llama/llama-3.1-405b-instruct', + description: 'Llama 3.1 70B Instruct 专为高质量对话而设计，在人类评估中表现突出，特别适合高交互场景。', + displayName: 'Llama 3.1 70B Instruct', + id: 'meta-llama/llama-3.1-70b-instruct', + pricing: { + input: 0.34, + output: 0.39, + }, type: 'chat', }, { @@ -33,6 +41,10 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'Llama 3 8B Instruct 优化了高质量对话场景，性能优于许多闭源模型。', displayName: 'Llama 3 8B Instruct', id: 'meta-llama/llama-3-8b-instruct', + pricing: { + input: 0.04, + output: 0.04, + }, type: 'chat', }, { @@ -40,6 +52,10 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'Llama 3 70B Instruct 优化用于高质量对话场景，在各类人类评估中表现优异。', displayName: 'Llama 3 70B Instruct', id: 'meta-llama/llama-3-70b-instruct', + pricing: { + input: 0.51, + output: 0.74, + }, type: 'chat', }, { @@ -48,14 +64,22 @@ const novitaChatModels: AIChatModelCard[] = [ displayName: 'Gemma 2 9B', enabled: true, id: 'google/gemma-2-9b-it', + pricing: { + input: 0.08, + output: 0.08, + }, type: 'chat', }, { - contextWindowTokens: 32_768, + contextWindowTokens: 131_072, description: 'Mistral Nemo 是多语言支持和高性能编程的7.3B参数模型。', displayName: 'Mistral Nemo', enabled: true, id: 'mistralai/mistral-nemo', + pricing: { + input: 0.17, + output: 0.17, + }, type: 'chat', }, { @@ -64,14 +88,10 @@ const novitaChatModels: AIChatModelCard[] = [ displayName: 'Mistral 7B Instruct', enabled: true, id: 'mistralai/mistral-7b-instruct', - type: 'chat', - }, - { - contextWindowTokens: 32_768, - description: 'WizardLM 2 7B 是微软AI最新的快速轻量化模型，性能接近于现有开源领导模型的10倍。', - displayName: 'WizardLM 2 7B', - enabled: true, - id: 'microsoft/wizardlm 2-7b', + pricing: { + input: 0.059, + output: 0.059, + }, type: 'chat', }, { @@ -80,6 +100,10 @@ const novitaChatModels: AIChatModelCard[] = [ displayName: 'WizardLM-2 8x22B', enabled: true, id: 'microsoft/wizardlm-2-8x22b', + pricing: { + input: 0.62, + output: 0.62, + }, type: 'chat', }, { @@ -87,6 +111,10 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'Dolphin Mixtral 8x22B 是一款为指令遵循、对话和编程设计的模型。', displayName: 'Dolphin Mixtral 8x22B', id: 'cognitivecomputations/dolphin-mixtral-8x22b', + pricing: { + input: 0.9, + output: 0.9, + }, type: 'chat', }, { @@ -94,13 +122,10 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'Hermes 2 Pro Llama 3 8B 是 Nous Hermes 2的升级版本，包含最新的内部开发的数据集。', displayName: 'Hermes 2 Pro Llama 3 8B', id: 'nousresearch/hermes-2-pro-llama-3-8b', - type: 'chat', - }, - { - contextWindowTokens: 32_768, - description: 'Hermes 2 Mixtral 8x7B DPO 是一款高度灵活的多模型合并，旨在提供卓越的创造性体验。', - displayName: 'Hermes 2 Mixtral 8x7B DPO', - id: 'Nous-Hermes-2-Mixtral-8x7B-DPO', + pricing: { + input: 0.14, + output: 0.14, + }, type: 'chat', }, { @@ -108,6 +133,10 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'MythoMax l2 13B 是一款合并了多个顶尖模型的创意与智能相结合的语言模型。', displayName: 'MythoMax l2 13B', id: 'gryphe/mythomax-l2-13b', + pricing: { + input: 0.09, + output: 0.09, + }, type: 'chat', }, { @@ -115,6 +144,238 @@ const novitaChatModels: AIChatModelCard[] = [ description: 'OpenChat 7B 是经过“C-RLFT（条件强化学习微调）”策略精调的开源语言模型库。', displayName: 'OpenChat 7B', id: 'openchat/openchat-7b', + pricing: { + input: 0.06, + output: 0.06, + }, + type: 'chat', + }, + { + abilities: { + reasoning: true, + }, + contextWindowTokens: 64_000, + displayName: 'Deepseek R1', + enabled: true, + id: 'deepseek/deepseek-r1', + pricing: { + input: 4, + output: 4, + }, + type: 'chat', + }, + { + contextWindowTokens: 64_000, + displayName: 'Deepseek V3', + enabled: true, + id: 'deepseek/deepseek_v3', + pricing: { + input: 0.89, + output: 0.89, + }, + type: 'chat', + }, + { + abilities: { + reasoning: true, + }, + contextWindowTokens: 32_000, + displayName: 'Deepseek R1 Distill Llama 70B', + id: 'deepseek/deepseek-r1-distill-llama-70b', + pricing: { + input: 0.8, + output: 0.8, + }, + type: 'chat', + }, + { + abilities: { + reasoning: true, + }, + contextWindowTokens: 64_000, + displayName: 'Deepseek R1 Distill Qwen 14B', + id: 'deepseek/deepseek-r1-distill-qwen-14b', + pricing: { + input: 0.15, + output: 0.15, + }, + type: 'chat', + }, + { + abilities: { + reasoning: true, + }, + contextWindowTokens: 64_000, + displayName: 'Deepseek R1 Distill Qwen 32B', + enabled: true, + id: 'deepseek/deepseek-r1-distill-qwen-32b', + pricing: { + input: 0.3, + output: 0.3, + }, + type: 'chat', + }, + { + contextWindowTokens: 8192, + displayName: 'L3 8B Stheno v3.2', + id: 'Sao10K/L3-8B-Stheno-v3.2', + pricing: { + input: 0.05, + output: 0.05, + }, + type: 'chat', + }, + { + abilities: { + reasoning: true, + }, + contextWindowTokens: 32_000, + displayName: 'Deepseek R1 Distill Llama 8B', + id: 'deepseek/deepseek-r1-distill-llama-8b', + pricing: { + input: 0.04, + output: 0.04, + }, + type: 'chat', + }, + { + contextWindowTokens: 32_000, + displayName: 'Qwen 2.5 72B Instruct', + id: 'qwen/qwen-2.5-72b-instruct', + pricing: { + input: 0.38, + output: 0.4, + }, + type: 'chat', + }, + { + contextWindowTokens: 16_000, + displayName: 'L3 70B Euryale v2.1', + id: 'sao10k/l3-70b-euryale-v2.1', + pricing: { + input: 1.48, + output: 1.48, + }, + type: 'chat', + }, + { + contextWindowTokens: 4096, + displayName: 'Airoboros L2 70B', + id: 'jondurbin/airoboros-l2-70b', + pricing: { + input: 0.5, + output: 0.5, + }, + type: 'chat', + }, + { + contextWindowTokens: 4096, + displayName: 'Nous Hermes Llama2 13B', + id: 'nousresearch/nous-hermes-llama2-13b', + pricing: { + input: 0.17, + output: 0.17, + }, + type: 'chat', + }, + { + contextWindowTokens: 4096, + displayName: 'OpenHermes 2.5 Mistral 7B', + id: 'teknium/openhermes-2.5-mistral-7b', + pricing: { + input: 0.17, + output: 0.17, + }, + type: 'chat', + }, + { + contextWindowTokens: 4096, + displayName: 'Midnight Rose 70B', + id: 'sophosympatheia/midnight-rose-70b', + pricing: { + input: 0.8, + output: 0.8, + }, + type: 'chat', + }, + { + contextWindowTokens: 8192, + displayName: 'L3 8B Lunaris', + id: 'sao10k/l3-8b-lunaris', + pricing: { + input: 0.05, + output: 0.05, + }, + type: 'chat', + }, + { + contextWindowTokens: 32_768, + displayName: 'Qwen 2 VL 72B Instruct', + id: 'qwen/qwen-2-vl-72b-instruct', + pricing: { + input: 0.45, + output: 0.45, + }, + type: 'chat', + }, + { + contextWindowTokens: 131_000, + displayName: 'Llama 3.2 1B Instruct', + id: 'meta-llama/llama-3.2-1b-instruct', + pricing: { + input: 0.02, + output: 0.02, + }, + type: 'chat', + }, + { + contextWindowTokens: 32_768, + displayName: 'Llama 3.2 11B Vision Instruct', + id: 'meta-llama/llama-3.2-11b-vision-instruct', + pricing: { + input: 0.06, + output: 0.06, + }, + type: 'chat', + }, + { + contextWindowTokens: 32_768, + displayName: 'Llama 3.2 3B Instruct', + id: 'meta-llama/llama-3.2-3b-instruct', + pricing: { + input: 0.03, + output: 0.05, + }, + type: 'chat', + }, + { + contextWindowTokens: 8192, + displayName: 'Llama 3.1 8B Instruct BF16', + id: 'meta-llama/llama-3.1-8b-instruct-bf16', + pricing: { + input: 0.06, + output: 0.06, + }, + type: 'chat', + }, + { + contextWindowTokens: 16_000, + displayName: 'L31 70B Euryale v2.2', + id: 'sao10k/l31-70b-euryale-v2.2', + pricing: { + input: 1.48, + output: 1.48, + }, + type: 'chat', + }, + { + contextWindowTokens: 32_768, + displayName: 'Qwen 2 7B Instruct', + id: 'qwen/qwen-2-7b-instruct', + pricing: { + input: 0.054, + output: 0.054, + }, type: 'chat', }, ]; From f1f7b36cac019d4be0637a5f2abcfb83d293362a Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 22:55:07 +0800 Subject: [PATCH 14/20] Update sensenova.ts --- src/config/aiModels/sensenova.ts | 87 +++++++++++++++++++++++++------- 1 file changed, 70 insertions(+), 17 deletions(-) diff --git a/src/config/aiModels/sensenova.ts b/src/config/aiModels/sensenova.ts index dbcd294c608b1..6b9f0d59297b6 100644 --- a/src/config/aiModels/sensenova.ts +++ b/src/config/aiModels/sensenova.ts @@ -1,5 +1,8 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://platform.sensenova.cn/pricing +// https://www.sensecore.cn/help/docs/model-as-a-service/nova/release + const sensenovaChatModels: AIChatModelCard[] = [ { abilities: { @@ -7,7 +10,43 @@ const sensenovaChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 131_072, description: - '最新版本模型 (V5.5)，128K上下文长度，在数学推理、英文对话、指令跟随以及长文本理解等领域能力显著提升，比肩GPT-4o', + '是基于V5.5的最新版本，较上版本在中英文基础能力，聊天，理科知识， 文科知识，写作，数理逻辑，字数控制 等几个维度的表现有显著提升。', + displayName: 'SenseChat 5.5 1202', + enabled: true, + id: 'SenseChat-5-1202', + pricing: { + currency: 'CNY', + input: 8, + output: 20, + }, + releasedAt: '2024-12-30', + type: 'chat', + }, + { + abilities: { + functionCall: true, + }, + contextWindowTokens: 32_768, + description: + '是最新的轻量版本模型，达到全量模型90%以上能力，显著降低推理成本。', + displayName: 'SenseChat Turbo 1202', + enabled: true, + id: 'SenseChat-Turbo-1202', + pricing: { + currency: 'CNY', + input: 0.3, + output: 0.6, + }, + releasedAt: '2024-12-30', + type: 'chat', + }, + { + abilities: { + functionCall: true, + }, + contextWindowTokens: 131_072, + description: + '最新版本模型 (V5.5)，128K上下文长度，在数学推理、英文对话、指令跟随以及长文本理解等领域能力显著提升，比肩GPT-4o。', displayName: 'SenseChat 5.5', enabled: true, id: 'SenseChat-5', @@ -20,27 +59,31 @@ const sensenovaChatModels: AIChatModelCard[] = [ }, { contextWindowTokens: 32_768, - description: '适用于快速问答、模型微调场景', - displayName: 'SenseChat 5.0 Turbo', + description: '最新版本模型 (V5.5)，支持多图的输入，全面实现模型基础能力优化，在对象属性识别、空间关系、动作事件识别、场景理解、情感识别、逻辑常识推理和文本理解生成上都实现了较大提升。', + displayName: 'SenseChat 5.5 Vision', enabled: true, - id: 'SenseChat-Turbo', + id: 'SenseChat-Vision', pricing: { currency: 'CNY', - input: 2, - output: 5, + input: 10, // 限时优惠 + output: 60, }, + releasedAt: '2024-09-12', type: 'chat', }, { + abilities: { + functionCall: true, + }, contextWindowTokens: 32_768, - description: - '32K上下文长度，在粤语的对话理解上超越了GPT-4，在知识、推理、数学及代码编写等多个领域均能与GPT-4 Turbo相媲美', - displayName: 'SenseChat 5.0 Cantonese', - id: 'SenseChat-5-Cantonese', + description: '适用于快速问答、模型微调场景', + displayName: 'SenseChat 5.0 Turbo', + enabled: true, + id: 'SenseChat-Turbo', pricing: { currency: 'CNY', - input: 27, - output: 27, + input: 2, + output: 5, }, type: 'chat', }, @@ -48,7 +91,6 @@ const sensenovaChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, description: '基础版本模型 (V4)，128K上下文长度，在长文本理解及生成等任务中表现出色', displayName: 'SenseChat 4.0 128K', - enabled: true, id: 'SenseChat-128K', pricing: { currency: 'CNY', @@ -61,7 +103,6 @@ const sensenovaChatModels: AIChatModelCard[] = [ contextWindowTokens: 32_768, description: '基础版本模型 (V4)，32K上下文长度，灵活应用于各类场景', displayName: 'SenseChat 4.0 32K', - enabled: true, id: 'SenseChat-32K', pricing: { currency: 'CNY', @@ -74,7 +115,6 @@ const sensenovaChatModels: AIChatModelCard[] = [ contextWindowTokens: 4096, description: '基础版本模型 (V4)，4K上下文长度，通用能力强大', displayName: 'SenseChat 4.0 4K', - enabled: true, id: 'SenseChat', pricing: { currency: 'CNY', @@ -83,9 +123,22 @@ const sensenovaChatModels: AIChatModelCard[] = [ }, type: 'chat', }, + { + contextWindowTokens: 32_768, + description: + '专门为适应香港地区的对话习惯、俚语及本地知识而设计，在粤语的对话理解上超越了GPT-4，在知识、推理、数学及代码编写等多个领域均能与GPT-4 Turbo相媲美。', + displayName: 'SenseChat 5.0 Cantonese', + id: 'SenseChat-5-Cantonese', + pricing: { + currency: 'CNY', + input: 27, + output: 27, + }, + type: 'chat', + }, { contextWindowTokens: 8192, - description: '标准版模型，8K上下文长度，高响应速度', + description: '拟人对话标准版模型，8K上下文长度，高响应速度', displayName: 'SenseChat Character', id: 'SenseChat-Character', pricing: { @@ -97,7 +150,7 @@ const sensenovaChatModels: AIChatModelCard[] = [ }, { contextWindowTokens: 32_768, - description: '高级版模型，32K上下文长度，能力全面提升，支持中/英文对话', + description: '拟人对话高级版模型，32K上下文长度，能力全面提升，支持中/英文对话', displayName: 'SenseChat Character Pro', id: 'SenseChat-Character-Pro', pricing: { From d0bee9162bc5d40844696c4782fccd00ed61e62b Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 23:04:04 +0800 Subject: [PATCH 15/20] Update taichu.ts --- src/config/aiModels/taichu.ts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/src/config/aiModels/taichu.ts b/src/config/aiModels/taichu.ts index 81dedf56a25c4..8c7d80e33d469 100644 --- a/src/config/aiModels/taichu.ts +++ b/src/config/aiModels/taichu.ts @@ -1,5 +1,7 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://docs.wair.ac.cn/maas/jiage.html + const taichuChatModels: AIChatModelCard[] = [ { abilities: { @@ -23,9 +25,9 @@ const taichuChatModels: AIChatModelCard[] = [ }, contextWindowTokens: 4096, description: '融合了图像理解、知识迁移、逻辑归因等能力，在图文问答领域表现突出', - displayName: 'Taichu 2.0V', + displayName: 'Taichu 2.0 VL', enabled: true, - id: 'taichu2_mm', + id: 'taichu_vl', pricing: { currency: 'CNY', input: 5, From 5ac3cc9402ed36ce09a3b4949f388960b5e03e9a Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 23:12:59 +0800 Subject: [PATCH 16/20] Update upstage.ts --- src/config/aiModels/upstage.ts | 35 +++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/src/config/aiModels/upstage.ts b/src/config/aiModels/upstage.ts index 4595fc04fe8d7..37fc7d94b27cd 100644 --- a/src/config/aiModels/upstage.ts +++ b/src/config/aiModels/upstage.ts @@ -1,6 +1,22 @@ import { AIChatModelCard } from '@/types/aiModel'; +// https://console.upstage.ai/docs/capabilities/chat + const upstageChatModels: AIChatModelCard[] = [ + { + contextWindowTokens: 32_768, + description: + 'Solar Pro 是 Upstage 推出的一款高智能LLM，专注于单GPU的指令跟随能力，IFEval得分80以上。目前支持英语，正式版本计划于2024年11月推出，将扩展语言支持和上下文长度。', + displayName: 'Solar Pro', + enabled: true, + id: 'solar-pro', + pricing: { + input: 0.25, + output: 0.25, + }, + releasedAt: '2024-11-26', + type: 'chat', + }, { abilities: { functionCall: true, @@ -10,7 +26,12 @@ const upstageChatModels: AIChatModelCard[] = [ 'Solar Mini 是一种紧凑型 LLM，性能优于 GPT-3.5，具备强大的多语言能力，支持英语和韩语，提供高效小巧的解决方案。', displayName: 'Solar Mini', enabled: true, - id: 'solar-1-mini-chat', + id: 'solar-mini', + pricing: { + input: 0.15, + output: 0.15, + }, + releasedAt: '2025-01-23', type: 'chat', }, { @@ -18,16 +39,8 @@ const upstageChatModels: AIChatModelCard[] = [ description: 'Solar Mini (Ja) 扩展了 Solar Mini 的能力，专注于日语，同时在英语和韩语的使用中保持高效和卓越性能。', displayName: 'Solar Mini (Ja)', - id: 'solar-1-mini-chat-ja', - type: 'chat', - }, - { - contextWindowTokens: 32_768, - description: - 'Solar Pro 是 Upstage 推出的一款高智能LLM，专注于单GPU的指令跟随能力，IFEval得分80以上。目前支持英语，正式版本计划于2024年11月推出，将扩展语言支持和上下文长度。', - displayName: 'Solar Pro', - enabled: true, - id: 'solar-pro', + id: 'solar-mini-ja', // deprecated on 2025-04-10 + releasedAt: '2025-01-23', type: 'chat', }, ]; From 6f32dd219c625b4e0b6863d1dd210d248b07480e Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 23:33:19 +0800 Subject: [PATCH 17/20] Update index.test.ts.snap --- .../openrouter/__snapshots__/index.test.ts.snap | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap b/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap index d0322ee9356d5..85d69cfec412e 100644 --- a/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap +++ b/src/libs/agent-runtime/openrouter/__snapshots__/index.test.ts.snap @@ -407,7 +407,7 @@ It has demonstrated strong performance compared to leading closed-source models To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).", "displayName": "Meta: Llama 3.1 70B Instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-70b-instruct", "maxTokens": undefined, @@ -439,7 +439,7 @@ It has demonstrated strong performance compared to leading closed-source models To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).", "displayName": "Meta: Llama 3.1 8B Instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-8b-instruct", "maxTokens": undefined, @@ -456,7 +456,7 @@ It has demonstrated strong performance compared to leading closed-source models To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).", "displayName": "Meta: Llama 3.1 405B Instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-405b-instruct", "maxTokens": undefined, From 260e9ac7b805197851446aa9d6d6765f1ed78d26 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 23:34:03 +0800 Subject: [PATCH 18/20] Update index.test.ts.snap --- .../agent-runtime/novita/__snapshots__/index.test.ts.snap | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/libs/agent-runtime/novita/__snapshots__/index.test.ts.snap b/src/libs/agent-runtime/novita/__snapshots__/index.test.ts.snap index fd4d625499a73..47e18238c8bee 100644 --- a/src/libs/agent-runtime/novita/__snapshots__/index.test.ts.snap +++ b/src/libs/agent-runtime/novita/__snapshots__/index.test.ts.snap @@ -26,7 +26,7 @@ exports[`NovitaAI > models > should get models 1`] = ` "contextWindowTokens": 8192, "description": "Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.", "displayName": "meta-llama/llama-3.1-8b-instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-8b-instruct", "reasoning": false, @@ -36,7 +36,7 @@ exports[`NovitaAI > models > should get models 1`] = ` "contextWindowTokens": 8192, "description": "Meta's latest class of models, Llama 3.1, has launched with a variety of sizes and configurations. The 70B instruct-tuned version is optimized for high-quality dialogue use cases. It has demonstrated strong performance in human evaluations compared to leading closed-source models.", "displayName": "meta-llama/llama-3.1-70b-instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-70b-instruct", "reasoning": false, @@ -46,7 +46,7 @@ exports[`NovitaAI > models > should get models 1`] = ` "contextWindowTokens": 32768, "description": "Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. This 405B instruct-tuned version is optimized for high-quality dialogue use cases. It has demonstrated strong performance compared to leading closed-source models, including GPT-4o and Claude 3.5 Sonnet, in evaluations.", "displayName": "meta-llama/llama-3.1-405b-instruct", - "enabled": true, + "enabled": false, "functionCall": false, "id": "meta-llama/llama-3.1-405b-instruct", "reasoning": false, From 5ac10dc48b2658d9382147b741a34c5f68e20c82 Mon Sep 17 00:00:00 2001 From: sxjeru Date: Wed, 19 Feb 2025 23:36:09 +0800 Subject: [PATCH 19/20] Update index.test.ts --- src/database/repositories/aiInfra/index.test.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/database/repositories/aiInfra/index.test.ts b/src/database/repositories/aiInfra/index.test.ts index d251b4381f048..a0bd37ebf832d 100644 --- a/src/database/repositories/aiInfra/index.test.ts +++ b/src/database/repositories/aiInfra/index.test.ts @@ -286,7 +286,7 @@ describe('AiInfraRepos', () => { expect(result).toEqual( expect.arrayContaining([ expect.objectContaining({ id: 'taichu_llm' }), - expect.objectContaining({ id: 'taichu2_mm' }), + expect.objectContaining({ id: 'taichu_vl' }), ]), ); }); From e47cf68da81ed26da433cc32973159eb1f152eab Mon Sep 17 00:00:00 2001 From: sxjeru Date: Sun, 23 Feb 2025 13:43:01 +0800 Subject: [PATCH 20/20] Update groq.ts --- src/config/aiModels/groq.ts | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/src/config/aiModels/groq.ts b/src/config/aiModels/groq.ts index 35890d2c9d86e..79b03e9cdffe2 100644 --- a/src/config/aiModels/groq.ts +++ b/src/config/aiModels/groq.ts @@ -197,7 +197,16 @@ const groqChatModels: AIChatModelCard[] = [ contextWindowTokens: 131_072, displayName: 'Qwen 2.5 32B', id: 'qwen-2.5-32b', - maxOutput: 8192, + pricing: { + input: 0.79, + output: 0.79, + }, + type: 'chat', + }, + { + contextWindowTokens: 131_072, + displayName: 'Qwen 2.5 Coder 32B', + id: 'qwen-2.5-coder-32b', pricing: { input: 0.79, output: 0.79,