diff --git a/conf/llm_factories.json b/conf/llm_factories.json index 3ea0feb3a..c7f5907e4 100644 --- a/conf/llm_factories.json +++ b/conf/llm_factories.json @@ -6,6 +6,34 @@ "tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION", "status": "1", "llm": [ + { + "llm_name": "gpt-4.5-preview", + "tags": "LLM,CHAT,128K", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "o3", + "tags": "LLM,CHAT,200K,IMAGE2TEXT", + "max_tokens": 200000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "o4-mini", + "tags": "LLM,CHAT,200K,IMAGE2TEXT", + "max_tokens": 200000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "o4-mini-high", + "tags": "LLM,CHAT,200K,IMAGE2TEXT", + "max_tokens": 200000, + "model_type": "chat", + "is_tools": true + }, { "llm_name": "gpt-4o-mini", "tags": "LLM,CHAT,128K,IMAGE2TEXT", @@ -175,6 +203,62 @@ "model_type": "chat", "is_tools": true }, + { + "llm_name": "qwen3-30b-a3b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-235b-a22b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-0.6b", + "tags": "LLM,CHAT,32k", + "max_tokens": 32000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-1.7b", + "tags": "LLM,CHAT,32k", + "max_tokens": 32000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-4b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-8b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-14b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen3-32b", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, { "llm_name": "qwen-long", "tags": "LLM,CHAT,10000K", @@ -184,8 +268,22 @@ }, { "llm_name": "qwen-turbo", - "tags": "LLM,CHAT,8K", - "max_tokens": 8191, + "tags": "LLM,CHAT,1M", + "max_tokens": 1000000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen-turbo-2025-04-28", + "tags": "LLM,CHAT,1M", + "max_tokens": 1000000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "qwen-turbo-latest", + "tags": "LLM,CHAT,1M", + "max_tokens": 1000000, "model_type": "chat", "is_tools": true }, @@ -203,6 +301,13 @@ "model_type": "chat", "is_tools": true }, + { + "llm_name": "qwen-plus-2025-04-28", + "tags": "LLM,CHAT,128k", + "max_tokens": 128000, + "model_type": "chat", + "is_tools": true + }, { "llm_name": "qwen-plus-latest", "tags": "LLM,CHAT,132k", @@ -870,6 +975,13 @@ "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT", "status": "1", "llm": [ + { + "llm_name": "gemini-2.5-flash-preview-04-17", + "tags": "LLM,CHAT,1024K,IMAGE2TEXT", + "max_tokens": 1048576, + "model_type": "image2text", + "is_tools": true + }, { "llm_name": "gemini-2.0-flash-001", "tags": "LLM,CHAT,1024K",