2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"factory_llm_infos": [
|
|
|
|
|
{
|
|
|
|
|
"name": "OpenAI",
|
|
|
|
|
"logo": "",
|
2024-11-20 12:16:36 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2025-11-12 09:38:06 +08:00
|
|
|
"rank": "999",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.openai.com/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2026-05-12 03:03:47 -07:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.5",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
2026-05-14 03:16:24 +01:00
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
2026-05-12 03:03:47 -07:00
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-12-12 17:35:08 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.2-pro",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.2",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-11-27 17:59:17 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.1",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.1-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-08 11:54:40 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,400k,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
2025-05-12 12:24:53 +02:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-mini",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-nano",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
|
|
|
|
"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
|
|
|
|
|
},
|
2024-08-08 12:30:40 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
2025-02-18 11:14:48 +08:00
|
|
|
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
2024-08-08 12:30:40 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-08 12:30:40 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
2025-02-18 11:14:48 +08:00
|
|
|
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-3.5-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-3.5-turbo-16k-0613",
|
|
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16385,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-ada-002",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-small",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-1",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 26214400,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4-32k",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
2024-09-19 16:55:18 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "tts-1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 2048,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-07-11 10:35:23 +08:00
|
|
|
{
|
|
|
|
|
"name": "xAI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "992",
|
2025-07-11 10:35:23 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3",
|
|
|
|
|
"tags": "LLM,CHAT,130k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-fast",
|
|
|
|
|
"tags": "LLM,CHAT,130k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini",
|
|
|
|
|
"tags": "LLM,CHAT,130k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini-mini-fast",
|
|
|
|
|
"tags": "LLM,CHAT,130k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-2-vision",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,32k",
|
2025-07-11 10:35:23 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-07-11 10:35:23 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-09-11 17:25:31 +08:00
|
|
|
{
|
|
|
|
|
"name": "TokenPony",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://ragflow.vip-api.tokenpony.cn/v1",
|
2025-09-11 17:25:31 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-8b",
|
2025-10-28 10:04:41 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-09-11 17:25:31 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3-0324",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-32b",
|
2025-10-28 10:04:41 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-09-11 17:25:31 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-10-28 10:04:41 +08:00
|
|
|
"llm_name": "kimi-k2-instruct-0905",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
2025-09-11 17:25:31 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-0528",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-480b",
|
|
|
|
|
"tags": "LLM,CHAT,1024k",
|
|
|
|
|
"max_tokens": 1024000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-10-28 10:04:41 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-a13b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-next-80b-a3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,1024k",
|
|
|
|
|
"max_tokens": 1024000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.2-exp",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.1-terminus",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-235b-a22b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-30b-a3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-11-28 12:10:04 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ocr",
|
|
|
|
|
"tags": "LLM,8k",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-235b-a22b-instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.6",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "minimax-m2",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-09-11 17:25:31 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"name": "Tongyi-Qianwen",
|
|
|
|
|
"logo": "",
|
2024-11-20 12:16:36 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,TTS,SPEECH2TEXT,MODERATION",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "994",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2026-03-20 20:32:00 +08:00
|
|
|
{
|
2026-06-26 17:30:16 +08:00
|
|
|
"llm_name": "qwen3-max-2026-01-23",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-instruct-flash",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.7-code",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-asr-flash-realtime-2025-10-27",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-mt-flash",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-flash-2025-10-15",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-35b-a3b",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-mt-plus",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-mt-turbo",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-5.2",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-max-preview",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-flash-2026-01-22",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-next",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.1",
|
|
|
|
|
"max_tokens": 163840,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-instruct-flash-realtime",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash-2025-09-15",
|
|
|
|
|
"max_tokens": 49152,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qvq-max",
|
2026-03-20 20:32:00 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-26 17:30:16 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vc-2026-01-22",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-qwen-7b",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-livetranslate-flash-2025-12-01",
|
|
|
|
|
"max_tokens": 49152,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2-thinking",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-math-plus",
|
|
|
|
|
"max_tokens": 3072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-2025-12-01",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vd-realtime-2026-01-15",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-flash-2026-04-16",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-max-preview",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v4-flash",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-math-plus-latest",
|
|
|
|
|
"max_tokens": 3072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qvq-plus",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash-2025-11-27",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-flash",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-instruct-flash-realtime-2026-01-22",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-max",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-math-turbo",
|
|
|
|
|
"max_tokens": 3072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ZHIPU/GLM-5.1",
|
|
|
|
|
"max_tokens": 202752,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash-2025-09-18",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-vl-ocr-2025-11-20",
|
|
|
|
|
"max_tokens": 30720,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"ocr",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-397b-a17b",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-plus-2026-04-02",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-35b-a3b",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi/kimi-k2.5",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash-realtime-2025-11-27",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-plus-2025-07-22",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-plus-2025-12-19",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash-realtime-2025-09-15",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-livetranslate-flash-realtime",
|
|
|
|
|
"max_tokens": 49152,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-vl-ocr-latest",
|
|
|
|
|
"max_tokens": 30720,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"ocr",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-omni-flash-2026-03-15",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-asr-flash-realtime",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-plus-2026-05-26",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vc-realtime-2025-11-27",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-2025-09-11",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-plus",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-max-2026-05-20",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-max-2025-09-23",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-instruct-flash-2026-01-26",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vd-realtime-2025-12-16",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-mt-lite",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash-realtime",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vd-2026-01-26",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi/kimi-k2.7-code",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
2026-03-20 20:32:00 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-07-31 14:42:32 +08:00
|
|
|
{
|
2026-06-26 17:30:16 +08:00
|
|
|
"llm_name": "qwen-plus-2025-01-25",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-27b",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-coder-turbo",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash-2025-12-01",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-max-preview",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-omni-flash-realtime-2025-12-01",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.5",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-coder-plus",
|
2025-07-31 14:42:32 +08:00
|
|
|
"max_tokens": 131072,
|
2026-06-26 17:30:16 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-plus-2025-09-23",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-plus",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-flash-character",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-omni-plus",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-flash",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi/kimi-k2.6",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-math-plus-0919",
|
|
|
|
|
"max_tokens": 3072,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-flash",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-plus",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"ocr",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash-realtime-2025-09-18",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-omni-plus-2026-03-15",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash-realtime",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-omni-turbo",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-livetranslate-flash-realtime-2025-09-22",
|
|
|
|
|
"max_tokens": 49152,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-flash",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v4-pro",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.6-27b",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-asr-flash-2026-02-10",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-asr-flash-realtime-2026-02-10",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ZHIPU/GLM-5",
|
|
|
|
|
"max_tokens": 202752,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-tts-2025-05-22",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-plus-2025-09-23",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-livetranslate-flash",
|
|
|
|
|
"max_tokens": 49152,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"speech2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.7-max-2026-06-08",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.6",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-tts-vc-realtime-2026-01-15",
|
|
|
|
|
"model_type": [
|
|
|
|
|
"tts"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-omni-flash",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"chat",
|
|
|
|
|
"speech2text",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-vl-ocr",
|
|
|
|
|
"max_tokens": 30720,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"ocr",
|
|
|
|
|
"image2text"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-122b-a10b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-07-31 14:42:32 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-12-11 13:55:01 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.2",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-02-12 17:52:29 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1",
|
|
|
|
|
"tags": "LLM,CHAT,64K",
|
|
|
|
|
"max_tokens": 65792,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
2025-04-15 09:19:07 +08:00
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3",
|
|
|
|
|
"tags": "LLM,CHAT,64K",
|
|
|
|
|
"max_tokens": 65792,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-qwen-1.5b",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-qwen-14b",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-qwen-32b",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-llama-8b",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-distill-llama-70b",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
2025-03-12 18:54:15 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwq-plus",
|
2025-04-01 11:06:03 +08:00
|
|
|
"tags": "LLM,CHAT,132k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
Refa: revise the implementation of LightRAG and enable response caching (#9828)
### What problem does this PR solve?
This revision performed a comprehensive check on LightRAG to ensure the
correctness of its implementation. It **did not involve** Entity
Resolution and Community Reports Generation. There is an example using
default entity types and the General chunking method, which shows good
results in both time and effectiveness. Moreover, response caching is
enabled for resuming failed tasks.
[The-Necklace.pdf](https://github.com/user-attachments/files/22042432/The-Necklace.pdf)
After:
```bash
Begin at:
Fri, 29 Aug 2025 16:48:03 GMT
Duration:
222.31 s
Progress:
16:48:04 Task has been received.
16:48:06 Page(1~7): Start to parse.
16:48:06 Page(1~7): OCR started
16:48:08 Page(1~7): OCR finished (1.89s)
16:48:11 Page(1~7): Layout analysis (3.72s)
16:48:11 Page(1~7): Table analysis (0.00s)
16:48:11 Page(1~7): Text merged (0.00s)
16:48:11 Page(1~7): Finish parsing.
16:48:12 Page(1~7): Generate 7 chunks
16:48:12 Page(1~7): Embedding chunks (0.29s)
16:48:12 Page(1~7): Indexing done (0.04s). Task done (7.84s)
16:48:17 Start processing for f421fb06849e11f0bdd32724b93a52b2: She had no dresses, no je...
16:48:17 Start processing for f421fb06849e11f0bdd32724b93a52b2: Her husband, already half...
16:48:17 Start processing for f421fb06849e11f0bdd32724b93a52b2: And this life lasted ten ...
16:48:17 Start processing for f421fb06849e11f0bdd32724b93a52b2: Then she asked, hesitatin...
16:49:30 Completed processing for f421fb06849e11f0bdd32724b93a52b2: She had no dresses, no je... after 1 gleanings, 21985 tokens.
16:49:30 Entities extraction of chunk 3 1/7 done, 12 nodes, 13 edges, 21985 tokens.
16:49:40 Completed processing for f421fb06849e11f0bdd32724b93a52b2: Finally, she replied, hes... after 1 gleanings, 22584 tokens.
16:49:40 Entities extraction of chunk 5 2/7 done, 19 nodes, 19 edges, 22584 tokens.
16:50:02 Completed processing for f421fb06849e11f0bdd32724b93a52b2: Then she asked, hesitatin... after 1 gleanings, 24610 tokens.
16:50:02 Entities extraction of chunk 0 3/7 done, 16 nodes, 28 edges, 24610 tokens.
16:50:03 Completed processing for f421fb06849e11f0bdd32724b93a52b2: And this life lasted ten ... after 1 gleanings, 24031 tokens.
16:50:04 Entities extraction of chunk 1 4/7 done, 24 nodes, 22 edges, 24031 tokens.
16:50:14 Completed processing for f421fb06849e11f0bdd32724b93a52b2: So they begged the jewell... after 1 gleanings, 24635 tokens.
16:50:14 Entities extraction of chunk 6 5/7 done, 27 nodes, 26 edges, 24635 tokens.
16:50:29 Completed processing for f421fb06849e11f0bdd32724b93a52b2: Her husband, already half... after 1 gleanings, 25758 tokens.
16:50:29 Entities extraction of chunk 2 6/7 done, 25 nodes, 35 edges, 25758 tokens.
16:51:35 Completed processing for f421fb06849e11f0bdd32724b93a52b2: The Necklace By Guy de Ma... after 1 gleanings, 27491 tokens.
16:51:35 Entities extraction of chunk 4 7/7 done, 39 nodes, 37 edges, 27491 tokens.
16:51:35 Entities and relationships extraction done, 147 nodes, 177 edges, 171094 tokens, 198.58s.
16:51:35 Entities merging done, 0.01s.
16:51:35 Relationships merging done, 0.01s.
16:51:35 ignored 7 relations due to missing entities.
16:51:35 generated subgraph for doc f421fb06849e11f0bdd32724b93a52b2 in 198.68 seconds.
16:51:35 run_graphrag f421fb06849e11f0bdd32724b93a52b2 graphrag_task_lock acquired
16:51:35 set_graph removed 0 nodes and 0 edges from index in 0.00s.
16:51:35 Get embedding of nodes: 9/147
16:51:35 Get embedding of nodes: 109/147
16:51:37 Get embedding of edges: 9/170
16:51:37 Get embedding of edges: 109/170
16:51:40 set_graph converted graph change to 319 chunks in 4.21s.
16:51:40 Insert chunks: 4/319
16:51:40 Insert chunks: 104/319
16:51:40 Insert chunks: 204/319
16:51:40 Insert chunks: 304/319
16:51:40 set_graph added/updated 147 nodes and 170 edges from index in 0.53s.
16:51:40 merging subgraph for doc f421fb06849e11f0bdd32724b93a52b2 into the global graph done in 4.79 seconds.
16:51:40 Knowledge Graph done (204.29s)
```
Before:
```bash
Begin at:
Fri, 29 Aug 2025 17:00:47 GMT
processDuration:
173.38 s
Progress:
17:00:49 Task has been received.
17:00:51 Page(1~7): Start to parse.
17:00:51 Page(1~7): OCR started
17:00:53 Page(1~7): OCR finished (1.82s)
17:00:57 Page(1~7): Layout analysis (3.64s)
17:00:57 Page(1~7): Table analysis (0.00s)
17:00:57 Page(1~7): Text merged (0.00s)
17:00:57 Page(1~7): Finish parsing.
17:00:57 Page(1~7): Generate 7 chunks
17:00:57 Page(1~7): Embedding chunks (0.31s)
17:00:57 Page(1~7): Indexing done (0.03s). Task done (7.88s)
17:00:57 created task graphrag
17:01:00 Task has been received.
17:02:17 Entities extraction of chunk 1 1/7 done, 9 nodes, 9 edges, 10654 tokens.
17:02:31 Entities extraction of chunk 2 2/7 done, 12 nodes, 13 edges, 11066 tokens.
17:02:33 Entities extraction of chunk 4 3/7 done, 9 nodes, 10 edges, 10433 tokens.
17:02:42 Entities extraction of chunk 5 4/7 done, 11 nodes, 14 edges, 11290 tokens.
17:02:52 Entities extraction of chunk 6 5/7 done, 13 nodes, 15 edges, 11039 tokens.
17:02:55 Entities extraction of chunk 3 6/7 done, 14 nodes, 13 edges, 11466 tokens.
17:03:32 Entities extraction of chunk 0 7/7 done, 19 nodes, 18 edges, 13107 tokens.
17:03:32 Entities and relationships extraction done, 71 nodes, 89 edges, 79055 tokens, 149.66s.
17:03:32 Entities merging done, 0.01s.
17:03:32 Relationships merging done, 0.01s.
17:03:32 ignored 1 relations due to missing entities.
17:03:32 generated subgraph for doc b1d9d3b6848711f0aacd7ddc0714c4d3 in 149.69 seconds.
17:03:32 run_graphrag b1d9d3b6848711f0aacd7ddc0714c4d3 graphrag_task_lock acquired
17:03:32 set_graph removed 0 nodes and 0 edges from index in 0.00s.
17:03:32 Get embedding of nodes: 9/71
17:03:33 Get embedding of edges: 9/88
17:03:34 set_graph converted graph change to 161 chunks in 2.27s.
17:03:34 Insert chunks: 4/161
17:03:34 Insert chunks: 104/161
17:03:34 set_graph added/updated 71 nodes and 88 edges from index in 0.28s.
17:03:34 merging subgraph for doc b1d9d3b6848711f0aacd7ddc0714c4d3 into the global graph done in 2.60 seconds.
17:03:34 Knowledge Graph done (153.18s)
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
- [x] Performance Improvement
2025-08-29 17:58:36 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-2025-07-28",
|
|
|
|
|
"tags": "LLM,CHAT,132k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-2025-07-14",
|
|
|
|
|
"tags": "LLM,CHAT,132k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-flash-2025-07-28",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-03-02 15:37:08 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-plus",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-plus-2026-02-15",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3.5-flash-2026-02-23",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-08 10:39:23 +08:00
|
|
|
{
|
2025-09-24 20:00:53 +08:00
|
|
|
"llm_name": "qwen3-max",
|
2025-09-08 10:39:23 +08:00
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-01 15:19:51 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-coder-480b-a35b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-30b-a3b-instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-30b-a3b-thinking-2507",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-30b-a3b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-24 20:00:53 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-plus",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,256k",
|
2025-09-24 20:00:53 +08:00
|
|
|
"max_tokens": 256000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-24 20:00:53 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-235b-a22b-instruct",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,128k",
|
2025-09-24 20:00:53 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-24 20:00:53 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-vl-235b-a22b-thinking",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,128k",
|
2025-09-24 20:00:53 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-24 20:00:53 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-01 15:19:51 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-235b-a22b-instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-235b-a22b-thinking-2507",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-235b-a22b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-24 20:00:53 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-next-80b-a3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-next-80b-a3b-thinking",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
|
|
|
|
"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
|
|
|
|
|
},
|
2024-10-21 12:11:08 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-long",
|
|
|
|
|
"tags": "LLM,CHAT,10000K",
|
|
|
|
|
"max_tokens": 1000000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-10-21 12:11:08 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-turbo",
|
2025-04-29 18:26:29 +08:00
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-01-03 19:55:42 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-max",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-01-03 19:55:42 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus",
|
2025-04-15 09:19:07 +08:00
|
|
|
"tags": "LLM,CHAT,132k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-2025-04-28",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-04-15 09:19:07 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-plus-latest",
|
|
|
|
|
"tags": "LLM,CHAT,132k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,2K",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2024-09-09 11:01:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "sambert-zhide-v1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "tts"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sambert-zhiru-v1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "tts"
|
|
|
|
|
},
|
2024-08-20 09:44:15 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-v3",
|
2024-08-28 10:14:19 +08:00
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2024-08-20 09:44:15 +08:00
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2025-06-11 15:32:05 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-v4",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-vl-max",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 765,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": false
|
2024-08-09 18:58:58 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen-vl-plus",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
2024-08-09 18:58:58 +08:00
|
|
|
"max_tokens": 765,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": false
|
2024-10-21 12:11:08 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gte-rerank",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "rerank"
|
2025-08-19 16:41:18 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-12-02 11:17:31 +08:00
|
|
|
"llm_name": "qwen3-asr-flash",
|
2025-08-19 16:41:18 +08:00
|
|
|
"tags": "SPEECH2TEXT,8k",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "speech2text"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-12-02 11:17:31 +08:00
|
|
|
"llm_name": "qwen3-asr-flash-2025-09-08",
|
2025-08-19 16:41:18 +08:00
|
|
|
"tags": "SPEECH2TEXT,8k",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "speech2text"
|
2025-09-23 09:34:30 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-04-20 11:39:17 +08:00
|
|
|
"llm_name": "gte-rerank-v2",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-rerank",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "rerank"
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "ZHIPU-AI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "993",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://open.bigmodel.cn/api/paas/v4",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2025-12-23 12:38:56 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.7",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-26 11:49:01 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
2025-08-26 11:49:01 +08:00
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5-x",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
2025-08-26 11:49:01 +08:00
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5-air",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
2025-08-26 11:49:01 +08:00
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5-airx",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
2025-08-26 11:49:01 +08:00
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5-flash",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
2025-08-26 11:49:01 +08:00
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-26 13:48:00 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4.5v",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,64",
|
2025-08-26 13:48:00 +08:00
|
|
|
"max_tokens": 64000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-08-26 13:48:00 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
2024-11-12 11:27:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-plus",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
2024-11-12 11:27:43 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-12 11:27:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-0520",
|
2025-08-26 13:48:00 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
2024-11-12 11:27:43 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-12 11:27:43 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
2024-08-20 09:44:15 +08:00
|
|
|
"llm_name": "glm-4",
|
2025-09-18 09:51:29 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-08-20 09:44:15 +08:00
|
|
|
"llm_name": "glm-4-airx",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 8000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-20 09:44:15 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-air",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-20 09:44:15 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-flash",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-20 09:44:15 +08:00
|
|
|
},
|
2024-11-12 11:27:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-flashx",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-12 11:27:43 +08:00
|
|
|
},
|
2024-08-20 09:44:15 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-long",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 1000000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-20 09:44:15 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-3-turbo",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4v",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 2000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-10-21 10:30:35 +08:00
|
|
|
"llm_name": "glm-4-9b",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-10-21 10:30:35 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm_name": "embedding-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2024-08-20 09:44:15 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embedding-3",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2025-10-14 09:32:45 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-asr",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "speech2text"
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Ollama",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "988",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": []
|
|
|
|
|
},
|
2025-02-24 10:12:20 +08:00
|
|
|
{
|
|
|
|
|
"name": "ModelScope",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
2024-07-19 15:50:28 +08:00
|
|
|
{
|
|
|
|
|
"name": "LocalAI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
2024-08-06 16:20:21 +08:00
|
|
|
{
|
|
|
|
|
"name": "OpenAI-API-Compatible",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
2025-11-12 09:38:06 +08:00
|
|
|
"llm": [],
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "985"
|
2024-08-06 16:20:21 +08:00
|
|
|
},
|
2025-02-26 16:04:53 +08:00
|
|
|
{
|
|
|
|
|
"name": "VLLM",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"name": "Moonshot",
|
|
|
|
|
"logo": "",
|
2025-11-07 19:52:57 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "995",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.moonshot.cn/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2025-07-16 13:23:04 +08:00
|
|
|
{
|
2025-08-01 12:40:58 +08:00
|
|
|
"llm_name": "kimi-thinking-preview",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
2025-07-16 13:23:04 +08:00
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-08-01 12:40:58 +08:00
|
|
|
"llm_name": "kimi-k2-0711-preview",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-07-16 13:23:04 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-08 19:00:52 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2-0905-preview",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-11-07 19:52:57 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2-thinking",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2-thinking-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-08 19:00:52 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2-turbo-preview",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-01-28 12:41:20 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.5",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-07-16 13:23:04 +08:00
|
|
|
{
|
2025-08-01 12:40:58 +08:00
|
|
|
"llm_name": "kimi-latest",
|
|
|
|
|
"tags": "LLM,CHAT,8k,32k,128k",
|
2025-07-16 13:23:04 +08:00
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-8k",
|
2025-11-07 19:52:57 +08:00
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-32k",
|
2025-11-07 19:52:57 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-128k",
|
2025-11-07 19:52:57 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-10-28 10:37:22 +08:00
|
|
|
},
|
2025-11-07 19:52:57 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-8k-vision-preview",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-07 19:52:57 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-32k-vision-preview",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-07 19:52:57 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-128k-vision-preview",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-07 19:52:57 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-10-28 10:37:22 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "moonshot-v1-auto",
|
|
|
|
|
"tags": "LLM,CHAT,",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "FastEmbed",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
2025-03-31 15:33:19 +08:00
|
|
|
"llm": []
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Xinference",
|
|
|
|
|
"logo": "",
|
2024-11-20 12:16:36 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,SPEECH2TEXT,MODERATION,TEXT RE-RANK",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "DeepSeek",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "996",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.deepseek.com/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
2026-04-24 13:07:59 +08:00
|
|
|
"llm_name": "deepseek-v4-flash",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,",
|
2026-04-24 13:07:59 +08:00
|
|
|
"max_tokens": 1000000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-04-24 13:07:59 +08:00
|
|
|
"llm_name": "deepseek-v4-pro",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,",
|
2026-04-24 13:07:59 +08:00
|
|
|
"max_tokens": 1000000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "VolcEngine",
|
|
|
|
|
"logo": "",
|
2025-10-17 11:43:22 +08:00
|
|
|
"tags": "LLM, TEXT EMBEDDING, IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2026-06-08 20:18:00 +08:00
|
|
|
"url": "https://ark.cn-beijing.volces.com/api/v3",
|
2025-10-17 11:43:22 +08:00
|
|
|
"llm": []
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "BaiChuan",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan2-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan2-Turbo-192k",
|
|
|
|
|
"tags": "LLM,CHAT,192K",
|
|
|
|
|
"max_tokens": 196608,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan3-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan3-Turbo-128k",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan4",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Baichuan-Text-Embedding",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Jina",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TEXT EMBEDDING, TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-v1-base-en",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-v1-turbo-en",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-v1-tiny-en",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-colbert-v1-en",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v2-base-en",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v2-base-de",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v2-base-es",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v2-base-code",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v2-base-zh",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
2024-12-02 03:06:39 +01:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-v2-base-multilingual",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v3",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8196,
|
|
|
|
|
"model_type": "embedding"
|
2025-12-01 14:24:35 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-embeddings-v4",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-10-23 23:02:27 +08:00
|
|
|
{
|
|
|
|
|
"name": "Builtin",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-small-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING,512",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-0.6B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
2024-07-17 15:32:51 +08:00
|
|
|
"name": "MiniMax",
|
2024-07-16 15:19:43 +08:00
|
|
|
"logo": "",
|
2025-12-02 14:43:44 +08:00
|
|
|
"tags": "LLM",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "987",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.minimaxi.com/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2026-06-02 17:28:48 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M3",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-03-18 06:20:10 -05:00
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.7",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.7-highspeed",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-03-12 20:41:46 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.5",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.5-highspeed",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-12-24 16:08:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.1",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
2025-12-02 14:43:44 +08:00
|
|
|
"llm_name": "MiniMax-M2",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
2024-07-16 15:19:43 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Mistral",
|
|
|
|
|
"logo": "",
|
2025-03-10 10:28:02 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,MODERATION",
|
2024-07-16 15:19:43 +08:00
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.mistral.ai/v1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "codestral-latest",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "mistral-large-latest",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "mistral-saba-latest",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2024-12-03 15:18:38 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "pixtral-large-latest",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,131k",
|
2025-03-10 10:28:02 +08:00
|
|
|
"max_tokens": 131000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-12-03 15:18:38 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ministral-3b-latest",
|
2025-03-10 10:28:02 +08:00
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "ministral-8b-latest",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "mistral-embed",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistral-moderation-latest",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2024-07-16 15:19:43 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "mistral-small-latest",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "pixtral-12b-2409",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "mistral-ocr-latest",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2024-12-03 15:18:38 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "open-mistral-nemo",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-12-03 15:18:38 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-03-10 10:28:02 +08:00
|
|
|
"llm_name": "open-codestral-mamba",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat"
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Azure-OpenAI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
2024-08-08 12:30:40 +08:00
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4o-mini",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,128K",
|
2024-08-08 12:30:40 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-08-08 12:30:40 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4o",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,128K",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-10-11 11:26:42 +08:00
|
|
|
"llm_name": "gpt-3.5-turbo",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-10-11 11:26:42 +08:00
|
|
|
"llm_name": "gpt-3.5-turbo-16k",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16385,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "text-embedding-ada-002",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "text-embedding-3-small",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "text-embedding-3-large",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "whisper-1",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 26214400,
|
|
|
|
|
"model_type": "speech2text"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4-turbo",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8191,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4-32k",
|
2024-07-16 15:19:43 +08:00
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2024-09-09 12:10:45 +08:00
|
|
|
"llm_name": "gpt-4-vision-preview",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
2024-07-16 15:19:43 +08:00
|
|
|
"max_tokens": 765,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Bedrock",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
2025-03-27 14:59:15 +08:00
|
|
|
"llm": []
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Gemini",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "997",
|
2024-07-16 15:19:43 +08:00
|
|
|
"llm": [
|
2025-11-19 13:17:22 +08:00
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-3-pro-preview",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2025-11-19 13:17:22 +08:00
|
|
|
},
|
2025-07-23 10:18:04 +08:00
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-2.5-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1024K,IMAGE2TEXT",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2025-07-23 10:18:04 +08:00
|
|
|
},
|
|
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-2.5-pro",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,1024K",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2025-07-23 10:18:04 +08:00
|
|
|
},
|
2025-04-29 18:26:29 +08:00
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-2.5-flash-lite",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1024K,IMAGE2TEXT",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2025-04-29 18:26:29 +08:00
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-2.0-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1024K",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2024-07-16 15:19:43 +08:00
|
|
|
},
|
2025-02-14 12:31:07 +07:00
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-2.0-flash-lite",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1024K",
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"is_tools": true
|
2025-02-08 10:19:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
"llm_name": "gemini-embedding-001",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-16 15:19:43 +08:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Groq",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemma2-9b-it",
|
|
|
|
|
"tags": "LLM,CHAT,15k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama3-70b-8192",
|
|
|
|
|
"tags": "LLM,CHAT,6k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama3-8b-8192",
|
|
|
|
|
"tags": "LLM,CHAT,30k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-08-27 11:42:00 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "llama-3.1-70b-versatile",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-27 11:42:00 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama-3.1-8b-instant",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-27 11:42:00 +08:00
|
|
|
},
|
2024-12-23 11:18:01 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "llama-3.3-70b-versatile",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-12-23 11:18:01 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama-3.3-70b-specdec",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-16 15:19:43 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "mixtral-8x7b-32768",
|
|
|
|
|
"tags": "LLM,CHAT,5k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "OpenRouter",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
2025-11-12 09:38:06 +08:00
|
|
|
"llm": [],
|
2026-06-10 14:59:27 +08:00
|
|
|
"rank": "989",
|
|
|
|
|
"url": "https://openrouter.ai/api/v1"
|
2024-07-19 16:26:12 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "StepFun",
|
|
|
|
|
"logo": "",
|
2026-02-05 12:47:04 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,SPEECH2TEXT,TTS",
|
2024-07-19 16:26:12 +08:00
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
2026-02-05 12:47:04 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "step-3",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,64k",
|
2026-02-05 12:47:04 +08:00
|
|
|
"max_tokens": 65536,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-02-05 12:47:04 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-2-mini",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-2-16k",
|
|
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-07-19 16:26:12 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "step-1-8k",
|
2024-07-24 10:49:37 +08:00
|
|
|
"tags": "LLM,CHAT,8k",
|
2024-07-19 16:26:12 +08:00
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-19 16:26:12 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-1-32k",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-19 16:26:12 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-1-256k",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-24 10:49:37 +08:00
|
|
|
},
|
2026-02-05 12:47:04 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "step-r1-v-mini",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,100k",
|
2026-02-05 12:47:04 +08:00
|
|
|
"max_tokens": 102400,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-02-05 12:47:04 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-07-24 10:49:37 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "step-1v-8k",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,8k",
|
2024-07-30 16:57:27 +08:00
|
|
|
"max_tokens": 8192,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2026-02-05 12:47:04 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-1v-32k",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,32k",
|
2026-02-05 12:47:04 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-02-05 12:47:04 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-1o-vision-32k",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,32k",
|
2026-02-05 12:47:04 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-02-05 12:47:04 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-1o-turbo-vision",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,IMAGE2TEXT,32k",
|
2026-02-05 12:47:04 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-02-05 12:47:04 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-tts-mini",
|
|
|
|
|
"tags": "TTS,1000c",
|
|
|
|
|
"max_tokens": 1000,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-tts-vivid",
|
|
|
|
|
"tags": "TTS,1000c",
|
|
|
|
|
"max_tokens": 1000,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "step-asr",
|
|
|
|
|
"tags": "SPEECH2TEXT,100MB",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
2024-07-19 16:26:12 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "NVIDIA",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING, TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "01-ai/yi-large",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "abacusai/dracarys-llama-3.1-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ai21labs/jamba-1.5-large-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ai21labs/jamba-1.5-mini-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "aisingapore/sea-lion-7b-instruct",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "baichuan-inc/baichuan2-13b-chat",
|
|
|
|
|
"tags": "LLM,CHAT,192K",
|
|
|
|
|
"max_tokens": 196608,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bigcode/starcoder2-7b",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,16K",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "bigcode/starcoder2-15b",
|
|
|
|
|
"tags": "LLM,CHAT,16K",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "databricks/dbrx-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/deepseek-r1",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-2b",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "google/gemma-7b",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-2-2b-it",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-2-9b-it",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-2-27b-it",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/codegemma-1.1-7b",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/codegemma-7b",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/recurrentgemma-2b",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/shieldgemma-9b",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ibm/granite-3.0-3b-a800m-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ibm/granite-3.0-8b-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "ibm/granite-34b-code-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ibm/granite-8b-code-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ibm/granite-guardian-3.0-8b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-05-12 12:24:53 +02:00
|
|
|
"model_type": "chat"
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "igenius / colosseum-355b_instruct_16k",
|
|
|
|
|
"tags": "LLM,CHAT,16K",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "igenius / italia_10b_instruct_16k",
|
|
|
|
|
"tags": "LLM,CHAT,16K",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v01",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "mediatek/breeze-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "meta/codellama-70b",
|
|
|
|
|
"tags": "LLM,CHAT,100K",
|
|
|
|
|
"max_tokens": 100000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama2-70b",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama3-8b",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama3-70b",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,",
|
2024-07-23 10:43:09 +08:00
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.1-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.1-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.1-405b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.2-1b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.2-3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.3-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-medium-128k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-medium-4k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "microsoft/phi-3-mini-128k-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-mini-4k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-small-128k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-small-8k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "microsoft/phi-3.5-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3.5-moe-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/codestral-22b-instruct-v0.1",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mamba-codestral-7b-v0.1",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "mistralai/mistral-2-large-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mathstral-7b-v01",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mistral-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mistral-7b-instruct-v0.3",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mixtral-8x7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mixtral-8x22b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,64K",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mistral-large",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "mistralai/mistral-small-24b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama3-chatqa-1.5-8b",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama-3.1-nemoguard-8b-content-safety",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama-3.1-nemoguard-8b-topic-control",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama-3.1-nemotron-51b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama-3.1-nemotron-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama-3.1-nemotron-70b-reward",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/llama3-chatqa-1.5-70b",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/mistral-nemo-minitron-8b-base",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/mistral-nemo-minitron-8b-8k-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/nemotron-4-340b-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nemotron-4-340b-reward",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nemotron-4-mini-hindi-4b-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nemotron-mini-4b-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nv-mistralai/mistral-nemo-12b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2.5-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2.5-coder-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rakuten/rakutenai-7b-chat",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2025-02-12 17:10:19 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "rakuten/rakutenai-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "seallms/seallm-7b-v2.5",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "snowflake/arctic",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tokyotech-llm/llama-3-swallow-70b-instruct-v01",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "thudm/chatglm3-6b",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tiiuae/falcon3-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
2024-07-23 10:43:09 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "upstage/solar-10.7b-instruct",
|
2025-02-12 17:10:19 +08:00
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-12 17:10:19 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "writer/palmyra-creative-122b",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "writer/palmyra-fin-70b-32k",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "writer/palmyra-med-70b-32k",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "writer/palmyra-med-70b",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "yentinglin/llama-3-taiwan-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zyphra/zamba2-7b-instruct",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
2024-07-23 10:43:09 +08:00
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-m3-unsupervised",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8192,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-m3-retromae",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8129,
|
|
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-large-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-base-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "BAAI/bge-small-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/embed-qa-4",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/llama-3.2-nv-embedqa-1b-v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
2024-07-23 10:43:09 +08:00
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/llama-3.2-nv-embedqa-1b-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 8192,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/llama-3.2-nv-rerankqa-1b-v1",
|
2024-07-23 10:43:09 +08:00
|
|
|
"tags": "RE-RANK,512",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/llama-3.2-nv-rerankqa-1b-v2",
|
|
|
|
|
"tags": "RE-RANK,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nvclip",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 1024,
|
2024-07-23 10:43:09 +08:00
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nv-embed-v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
2024-07-23 10:43:09 +08:00
|
|
|
"max_tokens": 4096,
|
2025-02-12 17:10:19 +08:00
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nv-embedqa-e5-v5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 1024,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nv-embedqa-mistral-7b-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
2024-07-23 10:43:09 +08:00
|
|
|
"max_tokens": 4096,
|
2025-02-12 17:10:19 +08:00
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/nv-rerankqa-mistral-4b-v3",
|
|
|
|
|
"tags": "RE-RANK,512",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "rerank"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "nvidia/rerank-qa-mistral-4b",
|
|
|
|
|
"tags": "RE-RANK,512",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "snowflake-arctic-embed-xs",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "snowflake-arctic-embed-s",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "snowflake-arctic-embed-m",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2024-07-23 10:43:09 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-02-12 17:10:19 +08:00
|
|
|
"llm_name": "snowflake-arctic-embed-m-long",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "snowflake-arctic-embed-l",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "adept/fuyu-8b",
|
|
|
|
|
"tags": "IMAGE2TEXT,1K",
|
|
|
|
|
"max_tokens": 1024,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/deplot",
|
|
|
|
|
"tags": "IMAGE2TEXT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/paligemma",
|
|
|
|
|
"tags": "IMAGE2TEXT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.2-11b-vision-instruct",
|
|
|
|
|
"tags": "IMAGE2TEXT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-3.2-90b-vision-instruct",
|
|
|
|
|
"tags": "IMAGE2TEXT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/florence-2",
|
|
|
|
|
"tags": "IMAGE2TEXT,1K",
|
|
|
|
|
"max_tokens": 1024,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/kosmos-2",
|
|
|
|
|
"tags": "IMAGE2TEXT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3-vision-128k-instruct",
|
|
|
|
|
"tags": "IMAGE2TEXT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-3.5-vision-instruct",
|
|
|
|
|
"tags": "IMAGE2TEXT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2025-02-12 17:52:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nvidia/neva-22b",
|
|
|
|
|
"tags": "IMAGE2TEXT,1K",
|
|
|
|
|
"max_tokens": 1024,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2024-07-23 10:43:09 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-07-24 12:46:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "LM-Studio",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-11-06 18:47:53 +08:00
|
|
|
"name": "Cohere",
|
2024-08-07 18:40:51 +08:00
|
|
|
"logo": "",
|
2026-06-03 15:55:45 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,SPEECH2TEXT",
|
2024-08-07 18:40:51 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "990",
|
2024-08-07 18:40:51 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-a-plus-05-2026",
|
2024-08-07 18:40:51 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-a-03-2025",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "command-r7b-12-2024",
|
2024-08-07 18:40:51 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-a-translate-08-2025",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2024-08-07 18:40:51 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-a-reasoning-08-2025",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "command-a-vision-07-2025",
|
2024-08-07 18:40:51 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-r-plus-08-2024",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "command-r-08-2024",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embed-v4.0",
|
|
|
|
|
"tags": "TEXT EMBEDDING,128k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "embedding"
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embed-english-v3.0",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embed-english-light-v3.0",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embed-multilingual-v3.0",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "embed-multilingual-light-v3.0",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "rerank-v4.0-pro",
|
|
|
|
|
"tags": "RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "rerank"
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "rerank-v4.0-fast",
|
|
|
|
|
"tags": "RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "rerank"
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "rerank-v3.5",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "rerank"
|
2024-08-07 18:40:51 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-english-v3.0",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-multilingual-v3.0",
|
|
|
|
|
"tags": "RE-RANK,4k",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-03 15:55:45 +08:00
|
|
|
"llm_name": "cohere-transcribe-03-2026",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "speech2text"
|
2024-08-07 18:40:51 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-08 12:09:50 +08:00
|
|
|
},
|
2024-08-12 10:15:21 +08:00
|
|
|
{
|
|
|
|
|
"name": "TogetherAI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
2024-08-12 11:06:25 +08:00
|
|
|
{
|
|
|
|
|
"name": "Upstage",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "solar-1-mini-chat",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "solar-1-mini-chat-ja",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "solar-embedding-1-large-query",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "solar-embedding-1-large-passage",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
]
|
2024-08-12 17:26:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"name": "NovitaAI",
|
2024-08-12 17:26:26 +08:00
|
|
|
"logo": "",
|
2025-04-28 13:35:09 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
2024-08-12 17:26:26 +08:00
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "qwen/qwen2.5-7b-instruct",
|
2025-03-04 11:35:25 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "meta-llama/llama-3.2-1b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-03-04 11:35:25 +08:00
|
|
|
"llm_name": "meta-llama/llama-3.2-3b-instruct",
|
2024-08-12 17:26:26 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "thudm/glm-4-9b-0414",
|
2025-03-04 11:35:25 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
2025-04-28 13:35:09 +08:00
|
|
|
"max_tokens": 32000,
|
2025-03-04 11:35:25 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "thudm/glm-z1-9b-0414",
|
2025-03-04 11:35:25 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
2025-04-28 13:35:09 +08:00
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat"
|
2025-03-04 11:35:25 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.1-8b-instruct-bf16",
|
2024-08-12 17:26:26 +08:00
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-12 17:26:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "meta-llama/llama-3.1-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16384,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-03-04 11:35:25 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-v3-0324",
|
2025-03-04 11:35:25 +08:00
|
|
|
"tags": "LLM,CHAT,128k",
|
2025-04-28 13:35:09 +08:00
|
|
|
"max_tokens": 128000,
|
2025-03-04 11:35:25 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-r1-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
2025-03-04 11:35:25 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Sao10K/L3-8B-Stheno-v3.2",
|
2024-08-12 17:26:26 +08:00
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "meta-llama/llama-3.3-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-12 17:26:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-llama-8b",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "mistralai/mistral-nemo",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 131072,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "meta-llama/llama-3-8b-instruct",
|
2025-03-04 11:35:25 +08:00
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2025-04-28 13:35:09 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-12 17:26:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-v3-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-12 17:26:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "mistralai/mistral-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-r1",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-qwen-14b",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
2024-08-12 17:26:26 +08:00
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-04-28 13:35:09 +08:00
|
|
|
"llm_name": "baai/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
2025-03-04 11:35:25 +08:00
|
|
|
"max_tokens": 8192,
|
2025-04-28 13:35:09 +08:00
|
|
|
"model_type": "embedding"
|
2024-08-12 17:26:26 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "SILICONFLOW",
|
|
|
|
|
"logo": "",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT,TTS,SPEECH2TEXT",
|
2024-08-13 16:09:10 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "986",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.siliconflow.cn/v1",
|
2024-08-13 16:09:10 +08:00
|
|
|
"llm": [
|
2025-08-06 10:57:03 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V4-Pro",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-08-06 10:57:03 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V4-Flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-08-06 10:57:03 +08:00
|
|
|
},
|
2024-08-13 16:09:10 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/moonshotai/Kimi-K2.6",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2025-02-05 13:43:40 +08:00
|
|
|
},
|
2025-02-07 10:32:52 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/zai-org/GLM-5.1",
|
|
|
|
|
"tags": "LLM,CHAT,205k",
|
|
|
|
|
"max_tokens": 205000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-07 10:32:52 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "nex-agi/Nex-N2-Pro",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2025-02-07 10:32:52 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "MiniMaxAI/MiniMax-M2.5",
|
|
|
|
|
"tags": "LLM,CHAT,197k",
|
|
|
|
|
"max_tokens": 197000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-07 10:32:52 +08:00
|
|
|
},
|
2025-02-05 13:43:40 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/MiniMaxAI/MiniMax-M2.5",
|
|
|
|
|
"tags": "LLM,CHAT,197k",
|
|
|
|
|
"max_tokens": 197000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.2",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/deepseek-ai/DeepSeek-V3.2",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.1-Terminus",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
2025-09-08 19:00:52 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.6-35B-A3B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-08 19:00:52 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-05-29 19:28:29 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.6-27B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-05-29 19:28:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-397B-A17B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2026-05-29 19:28:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-08 19:00:52 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-122B-A10B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-08 19:00:52 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-08-13 16:09:10 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-35B-A3B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-27B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-9B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2025-02-05 13:43:40 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3.5-4B",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2025-02-05 13:43:40 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1",
|
|
|
|
|
"tags": "LLM,CHAT,160k",
|
|
|
|
|
"max_tokens": 160000,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/deepseek-ai/DeepSeek-R1",
|
|
|
|
|
"tags": "LLM,CHAT,160k",
|
|
|
|
|
"max_tokens": 160000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3",
|
|
|
|
|
"tags": "LLM,CHAT,160k",
|
|
|
|
|
"max_tokens": 160000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/deepseek-ai/DeepSeek-V3",
|
|
|
|
|
"tags": "LLM,CHAT,160k",
|
|
|
|
|
"max_tokens": 160000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
2025-02-05 13:43:40 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "stepfun-ai/Step-3.5-Flash",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
2026-06-10 15:35:21 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-32B-Instruct",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-32B-Thinking",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-8B-Instruct",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-8B-Thinking",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
2025-02-05 13:43:40 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-30B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2025-02-05 13:43:40 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-30B-A3B-Thinking",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Captioner",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
2024-11-05 13:58:29 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "inclusionAI/Ling-flash-2.0",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-05 13:58:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "inclusionAI/Ling-mini-2.0",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-05 13:58:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "tencent/Hunyuan-MT-7B",
|
2024-11-05 13:58:29 +08:00
|
|
|
"tags": "LLM,CHAT,32k",
|
2025-08-06 10:57:03 +08:00
|
|
|
"max_tokens": 32000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
2024-11-05 13:58:29 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "ByteDance-Seed/Seed-OSS-36B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "zai-org/GLM-4.5V",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
|
|
|
|
"is_tools": true
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
2026-03-02 15:37:08 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "zai-org/GLM-4.5-Air",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-30B-A3B-Instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 256000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-05-29 19:28:29 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "tencent/Hunyuan-A13B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-05-29 19:28:29 +08:00
|
|
|
"model_type": "chat",
|
2026-06-10 15:35:21 +08:00
|
|
|
"is_tools": false
|
2026-05-29 19:28:29 +08:00
|
|
|
},
|
2026-03-02 15:37:08 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
2026-06-10 15:35:21 +08:00
|
|
|
"is_tools": false
|
2026-03-02 15:37:08 +08:00
|
|
|
},
|
2026-05-29 19:28:29 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-05-29 19:28:29 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-03-02 15:37:08 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-14B",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-8B",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "THUDM/GLM-4-32B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "THUDM/GLM-Z1-9B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "THUDM/GLM-4-9B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen2.5-72B-Instruct-128K",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen2.5-72B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen2.5-32B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen2.5-14B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen2.5-7B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/Qwen/Qwen2.5-7B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2026-03-02 15:37:08 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-08-13 16:09:10 +08:00
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-VL-Embedding-8B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-8B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding",
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-4B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-0.6B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding",
|
2025-05-14 19:46:27 +08:00
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "BAAI/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-05-14 19:46:27 +08:00
|
|
|
"llm_name": "BAAI/bge-large-en-v1.5",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "TEXT EMBEDDING,512",
|
2024-08-13 16:09:10 +08:00
|
|
|
"max_tokens": 512,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "BAAI/bge-large-zh-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING,512",
|
2025-05-14 19:46:27 +08:00
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
},
|
|
|
|
|
{
|
2026-06-10 15:35:21 +08:00
|
|
|
"llm_name": "Pro/BAAI/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-VL-Reranker-8B",
|
|
|
|
|
"tags": "TEXT RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32000,
|
2025-05-14 19:46:27 +08:00
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
2026-06-10 15:35:21 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-8B",
|
|
|
|
|
"tags": "TEXT RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-4B",
|
|
|
|
|
"tags": "TEXT RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-0.6B",
|
|
|
|
|
"tags": "TEXT RE-RANK,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-reranker-v2-m3",
|
|
|
|
|
"tags": "TEXT RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Pro/BAAI/bge-reranker-v2-m3",
|
|
|
|
|
"tags": "TEXT RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "fnlp/MOSS-TTSD-v0.5",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 26214400,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "FunAudioLLM/CosyVoice2-0.5B",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 26214400,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
2024-08-13 16:09:10 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-15 10:02:36 +08:00
|
|
|
},
|
2026-03-02 15:37:42 +08:00
|
|
|
{
|
|
|
|
|
"name": "siliconflow_intl",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT,TTS",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMaxAI/MiniMax-M2.5",
|
|
|
|
|
"tags": "LLM,CHAT,197k",
|
|
|
|
|
"max_tokens": 197000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/GLM-5",
|
|
|
|
|
"tags": "LLM,CHAT,205k",
|
|
|
|
|
"max_tokens": 205000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "stepfun-ai/Step-3.5-Flash",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/Kimi-K2.5",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMaxAI/MiniMax-M2.1",
|
|
|
|
|
"tags": "LLM,CHAT,197k",
|
|
|
|
|
"max_tokens": 197000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/GLM-4.7",
|
|
|
|
|
"tags": "LLM,CHAT,205k",
|
|
|
|
|
"max_tokens": 205000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.2",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.2-Exp",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/GLM-4.6V",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.1-Terminus",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3.1",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1",
|
|
|
|
|
"tags": "LLM,CHAT,154k",
|
|
|
|
|
"max_tokens": 154000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nex-agi/DeepSeek-V3.1-Nex-N1",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-VL-32B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-VL-32B-Thinking",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/GLM-4.5V",
|
|
|
|
|
"tags": "LLM,CHAT,66k",
|
|
|
|
|
"max_tokens": 66000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "inclusionAI/Ling-mini-2.0",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "inclusionAI/Ring-flash-2.0",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "inclusionAI/Ling-flash-2.0",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tencent/Hunyuan-MT-7B",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Captioner",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,65k",
|
|
|
|
|
"max_tokens": 65000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Next-80B-A3B-Thinking",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-30B-A3B-Thinking-2507",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-30B-A3B-Instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-235B-A22B-Instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ByteDance-Seed/Seed-OSS-36B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262k",
|
|
|
|
|
"max_tokens": 262000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baidu/ERNIE-4.5-300B-A47B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tencent/Hunyuan-A13B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/Kimi-K2-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-14B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-8B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-8B",
|
|
|
|
|
"tags": "LLM,RE-RANK,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-8B",
|
|
|
|
|
"tags": "LLM,EMBEDDING,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-4B",
|
|
|
|
|
"tags": "LLM,RE-RANK,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-4B",
|
|
|
|
|
"tags": "LLM,EMBEDDING,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Reranker-0.6B",
|
|
|
|
|
"tags": "LLM,RE-RANK,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-0.6B",
|
|
|
|
|
"tags": "LLM,EMBEDDING,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "THUDM/GLM-Z1-32B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "THUDM/GLM-4-32B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "THUDM/GLM-Z1-9B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "THUDM/GLM-4-9B-0414",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/QwQ-32B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-Coder-32B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-72B-Instruct-128K",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/deepseek-vl2",
|
|
|
|
|
"tags": "LLM,CHAT,4k",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-72B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-32B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-14B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen2.5-7B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,33k",
|
|
|
|
|
"max_tokens": 33000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "IndexTeam/IndexTTS-2",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 1000,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-02-17 12:03:26 +08:00
|
|
|
{
|
|
|
|
|
"name": "PPIO",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1/community",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-v3/community",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-v3",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-llama-70b",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-qwen-32b",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-qwen-14b",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1-distill-llama-8b",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen-2.5-72b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-17 12:03:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen-2-vl-72b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.2-3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2.5-32b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baichuan/baichuan2-13b-chat",
|
|
|
|
|
"tags": "LLM,CHAT,14k",
|
|
|
|
|
"max_tokens": 14336,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.1-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-17 12:03:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.1-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-02-17 12:03:26 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "01-ai/yi-1.5-34b-chat",
|
|
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "01-ai/yi-1.5-9b-chat",
|
|
|
|
|
"tags": "LLM,CHAT,16k",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "thudm/glm-4-9b-chat",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen-2-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2024-08-19 10:36:57 +08:00
|
|
|
{
|
|
|
|
|
"name": "Replicate",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
2026-06-11 15:08:33 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-4-maverick-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/llama-4-scout-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/meta-llama-3-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta/meta-llama-3-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "replicate/all-mpnet-base-v2:b6b7585c9640cd7a9572c6e129c9549d79c9c31f0d3fdce7baac7c67ca38f305",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 384,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ibm-granite/granite-embedding-278m-multilingual:1f76d42a05f120e12272746d5a2d86b525c13420773f795a4cbef9117d8685f1",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"rank": "987",
|
|
|
|
|
"url": "https://api.replicate.com"
|
2024-08-20 15:27:13 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Tencent Hunyuan",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.hunyuan.cloud.tencent.com/v1",
|
2024-08-20 15:27:13 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-pro",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-20 15:27:13 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-standard",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-standard-256K",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-lite",
|
|
|
|
|
"tags": "LLM,CHAT,256k",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hunyuan-vision",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT,8k",
|
|
|
|
|
"max_tokens": 8192,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
]
|
2024-08-20 15:27:13 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-20 16:56:42 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "XunFei Spark",
|
|
|
|
|
"logo": "",
|
2024-11-20 12:16:36 +08:00
|
|
|
"tags": "LLM,TTS",
|
2024-08-20 16:56:42 +08:00
|
|
|
"status": "1",
|
2026-06-08 14:54:59 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-Max",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-Max-32K",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-Lite",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-Pro",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-Pro-128K",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Spark-4.0-Ultra",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true,
|
2026-06-10 15:35:21 +08:00
|
|
|
"features": [
|
|
|
|
|
"is_tools",
|
|
|
|
|
"thinking"
|
|
|
|
|
]
|
2026-06-08 14:54:59 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-22 16:45:15 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "BaiduYiyan",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2024-08-26 15:19:43 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Fish Audio",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2024-08-27 11:47:11 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Tencent Cloud",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2024-08-29 13:30:06 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Anthropic",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "998",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.anthropic.com/",
|
2024-08-29 13:30:06 +08:00
|
|
|
"llm": [
|
2026-06-02 17:29:18 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-8",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-7",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-6",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-08-06 10:57:03 +08:00
|
|
|
{
|
2025-11-27 17:59:17 +08:00
|
|
|
"llm_name": "claude-opus-4-5-20251101",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-08-06 10:57:03 +08:00
|
|
|
"llm_name": "claude-opus-4-1-20250805",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-05-23 13:35:59 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-20250514",
|
2025-08-06 10:57:03 +08:00
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2025-05-23 13:35:59 +08:00
|
|
|
"max_tokens": 204800,
|
2025-08-06 10:57:03 +08:00
|
|
|
"model_type": "chat",
|
2025-05-23 13:35:59 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2026-06-02 17:29:18 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-6",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-09-30 12:04:14 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-5-20250929",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
|
|
|
|
"max_tokens": 204800,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2025-05-23 13:35:59 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
2025-08-06 10:57:03 +08:00
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2025-05-23 13:35:59 +08:00
|
|
|
"max_tokens": 204800,
|
2025-08-06 10:57:03 +08:00
|
|
|
"model_type": "chat",
|
2025-05-23 13:35:59 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
2024-08-29 13:30:06 +08:00
|
|
|
{
|
2025-03-24 12:34:57 +08:00
|
|
|
"llm_name": "claude-3-7-sonnet-20250219",
|
2025-08-06 10:57:03 +08:00
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2024-08-29 13:30:06 +08:00
|
|
|
"max_tokens": 204800,
|
2025-08-06 10:57:03 +08:00
|
|
|
"model_type": "chat",
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-08-29 13:30:06 +08:00
|
|
|
},
|
2024-11-14 10:30:16 +05:30
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-5-sonnet-20241022",
|
2025-08-06 10:57:03 +08:00
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2024-11-14 10:30:16 +05:30
|
|
|
"max_tokens": 204800,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-11-14 10:30:16 +05:30
|
|
|
},
|
2024-08-29 13:30:06 +08:00
|
|
|
{
|
2025-08-06 10:57:03 +08:00
|
|
|
"llm_name": "claude-3-5-haiku-20241022",
|
|
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2024-08-29 13:30:06 +08:00
|
|
|
"max_tokens": 204800,
|
2025-03-26 17:31:18 +08:00
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2024-08-29 13:30:06 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-haiku-20240307",
|
2025-08-06 10:57:03 +08:00
|
|
|
"tags": "LLM,CHAT,IMAGE2TEXT,200k",
|
2024-08-29 13:30:06 +08:00
|
|
|
"max_tokens": 204800,
|
2025-08-06 10:57:03 +08:00
|
|
|
"model_type": "chat",
|
2025-03-26 17:31:18 +08:00
|
|
|
"is_tools": true
|
2024-08-29 13:30:06 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-08-29 16:14:49 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "Voyage AI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TEXT EMBEDDING, TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
2026-06-02 17:29:18 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-4-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-4",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-4-lite",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2025-07-16 10:41:06 +07:00
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-3.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-3.5-lite",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-code-3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2025-06-03 11:56:59 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-multimodal-3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,Chat,IMAGE2TEXT,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2024-08-29 16:14:49 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-large-2-instruct",
|
|
|
|
|
"tags": "TEXT EMBEDDING,16000",
|
|
|
|
|
"max_tokens": 16000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-finance-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-multilingual-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-law-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,16000",
|
|
|
|
|
"max_tokens": 16000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-code-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,16000",
|
|
|
|
|
"max_tokens": 16000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-large-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,16000",
|
|
|
|
|
"max_tokens": 16000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,4000",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
2024-12-02 03:06:39 +01:00
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "voyage-3-lite",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
2025-03-12 18:54:15 +08:00
|
|
|
},
|
2024-08-29 16:14:49 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-1",
|
|
|
|
|
"tags": "RE-RANK, 8000",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-lite-1",
|
|
|
|
|
"tags": "RE-RANK, 4000",
|
|
|
|
|
"max_tokens": 4000,
|
|
|
|
|
"model_type": "rerank"
|
2024-12-02 03:06:39 +01:00
|
|
|
},
|
2026-06-02 17:29:18 +08:00
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-2.5",
|
|
|
|
|
"tags": "RE-RANK, 32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-2.5-lite",
|
|
|
|
|
"tags": "RE-RANK, 32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
2024-12-02 03:06:39 +01:00
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-2",
|
|
|
|
|
"tags": "RE-RANK, 16000",
|
|
|
|
|
"max_tokens": 16000,
|
|
|
|
|
"model_type": "rerank"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "rerank-2-lite",
|
|
|
|
|
"tags": "RE-RANK, 8000",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "rerank"
|
2024-08-29 16:14:49 +08:00
|
|
|
}
|
|
|
|
|
]
|
2024-09-02 12:06:41 +08:00
|
|
|
},
|
2025-06-30 09:22:31 +08:00
|
|
|
{
|
|
|
|
|
"name": "GiteeAI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT,SPEECH2TEXT,TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://ai.gitee.com/v1/",
|
2025-06-30 09:22:31 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ERNIE-4.5-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ERNIE-X1-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "DeepSeek-R1",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 65792,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "DeepSeek-V3",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 65792,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-235B-A22B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-30B-A3B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-8B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-4B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-0.6B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "QwQ-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "DeepSeek-R1-Distill-Qwen-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 65792,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "DeepSeek-R1-Distill-Qwen-14B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 65792,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "DeepSeek-R1-Distill-Qwen-1.5B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 65792,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2.5-72B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2.5-32B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2.5-14B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2.5-7B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2-72B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2-7B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "GLM-4-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "GLM-4-9B-0414",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-4-9b-chat",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "internlm3-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Yi-34B-Chat",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "ERNIE-4.5-Turbo-VL",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 4096,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2.5-VL-32B-Instruct",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2-VL-72B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 4096,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Align-DS-V",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 4096,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "InternVL3-78B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "InternVL3-38B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "InternVL2.5-78B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "InternVL2.5-26B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 16384,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "InternVL2-8B",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 8192,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen2-Audio-7B-Instruct",
|
|
|
|
|
"tags": "LLM,SPEECH2TEXT,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-base",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-large",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-large-v3-turbo",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-large-v3",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "SenseVoiceSmall",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Reranker-8B",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK,32K",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 32768,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Reranker-4B",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK,32K",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 32768,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Reranker-0.6B",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK,32K",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 32768,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Embedding-8B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Embedding-4B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen3-Embedding-0.6B",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-clip-v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-clip-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-m0",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK,10K",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 10240,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bce-embedding-base_v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bce-reranker-base_v1",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 512,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bge-reranker-v2-m3",
|
2026-02-02 13:43:16 +08:00
|
|
|
"tags": "TEXT RE-RANK",
|
2025-06-30 09:22:31 +08:00
|
|
|
"max_tokens": 8192,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank",
|
2025-06-30 09:22:31 +08:00
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bge-large-zh-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 1024,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "bge-small-zh-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "nomic-embed-code",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "all-mpnet-base-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 512,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2024-09-02 12:06:41 +08:00
|
|
|
{
|
|
|
|
|
"name": "Google Cloud",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2024-09-27 19:15:38 +08:00
|
|
|
},
|
|
|
|
|
{
|
2024-11-05 13:58:29 +08:00
|
|
|
"name": "HuggingFace",
|
|
|
|
|
"logo": "",
|
2025-03-06 10:44:04 +08:00
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
2024-11-05 13:58:29 +08:00
|
|
|
"status": "1",
|
2026-06-03 10:17:12 +08:00
|
|
|
"rank": "991",
|
2024-11-05 13:58:29 +08:00
|
|
|
"llm": []
|
2025-01-15 14:15:58 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "GPUStack",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,SPEECH2TEXT,TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2025-07-23 18:10:35 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "DeepInfra",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,SPEECH2TEXT,MODERATION",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/Kimi-K2-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/Voxtral-Small-24B-2507",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"model_type": "speech2text"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/Voxtral-Mini-3B-2507",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"model_type": "speech2text"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-0528-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-235B-A22B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-30B-A3B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-14B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3-0324-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-0528",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3-0324",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/Devstral-Small-2507",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-Guard-4-12B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/QwQ-32B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "anthropic/claude-4-opus",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "anthropic/claude-4-sonnet",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemini-2.5-pro",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-3-27b-it",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-3-12b-it",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-3-4b-it",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "hexgrad/Kokoro-82M",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"model_type": "tts"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "canopylabs/orpheus-3b-0.1-ft",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"model_type": "tts"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sesame/csm-1b",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"model_type": "tts"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/Phi-4-multimodal-instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-ai/DeepSeek-V3",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/Llama-3.3-70B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "microsoft/phi-4",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"model_type": "chat"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "openai/whisper-large-v3-turbo",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"model_type": "speech2text"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-base-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-en-icl",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-large-en-v1.5",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "BAAI/bge-m3-multi",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-0.6B",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-4B",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Embedding-8B",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "intfloat/e5-base-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "intfloat/e5-large-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "intfloat/multilingual-e5-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "intfloat/multilingual-e5-large-instruct",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/all-MiniLM-L12-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/all-MiniLM-L6-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/all-mpnet-base-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/clip-ViT-B-32",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/clip-ViT-B-32-multilingual-v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sentence-transformers/paraphrase-MiniLM-L6-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "shibing624/text2vec-base-chinese",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "thenlper/gte-base",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "thenlper/gte-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
]
|
2025-07-31 14:48:30 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "302.AI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-chat",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "chatgpt-4o-latest",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama3.3-70b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-reasoner",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM",
|
2025-07-31 14:48:30 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-07-31 14:48:30 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-7-sonnet-20250219",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-7-sonnet-latest",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-beta",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini-beta",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o3",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o4-mini",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-235b-a22b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-32b",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro-preview-05-06",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "llama-4-maverick",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
|
|
|
|
"tags": "LLM,CHAT",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-20250514",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM",
|
2025-07-31 14:48:30 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-07-31 14:48:30 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM",
|
2025-07-31 14:48:30 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-07-31 14:48:30 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-clip-v2",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-m0",
|
|
|
|
|
"tags": "TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"max_tokens": 10240,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
2025-09-08 19:00:52 +08:00
|
|
|
},
|
2025-09-18 09:51:29 +08:00
|
|
|
{
|
|
|
|
|
"name": "CometAPI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "chatgpt-4o-latest",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-mini",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-nano",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o4-mini-2025-04-16",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o3-pro-2025-06-10",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-1-20250805",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-1-20250805-thinking",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514-thinking",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-7-sonnet-latest",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-5-haiku-latest",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-lite",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4-0709",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-2-image-1212",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,32k,IMAGE2TEXT",
|
2025-09-18 09:51:29 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-09-18 09:51:29 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.1",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-0528",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-chat",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-reasoner",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"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-coder-plus-2025-07-22",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-ada-002",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-small",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-1",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 26214400,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tts-1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-09-08 19:00:52 +08:00
|
|
|
{
|
2025-11-11 16:58:47 +08:00
|
|
|
"name": "LongCat",
|
2025-09-08 19:00:52 +08:00
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.longcat.chat/openai",
|
2025-09-08 19:00:52 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "LongCat-Flash-Chat",
|
|
|
|
|
"tags": "LLM,CHAT,8000",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-09-30 12:04:14 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "LongCat-Flash-Thinking",
|
|
|
|
|
"tags": "LLM,CHAT,8000",
|
|
|
|
|
"max_tokens": 8000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
2025-09-08 19:00:52 +08:00
|
|
|
}
|
|
|
|
|
]
|
2025-10-09 11:14:49 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "DeerAPI",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "chatgpt-4o-latest",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-mini",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-nano",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o4-mini-2025-04-16",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o3-pro-2025-06-10",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-1-20250805",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-1-20250805-thinking",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514-thinking",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200k,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-7-sonnet-latest",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-5-haiku-latest",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-lite",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 1000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4-0709",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-2-image-1212",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,32k,IMAGE2TEXT",
|
2025-10-09 11:14:49 +08:00
|
|
|
"max_tokens": 32768,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-10-09 11:14:49 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3.1",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-v3",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-r1-0528",
|
|
|
|
|
"tags": "LLM,CHAT,164k",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-chat",
|
|
|
|
|
"tags": "LLM,CHAT,32k",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-reasoner",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 64000,
|
|
|
|
|
"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-coder-plus-2025-07-22",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-ada-002",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-small",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-1",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 26214400,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tts-1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 2048,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
2025-11-17 19:47:46 +08:00
|
|
|
},
|
|
|
|
|
{
|
2025-11-19 19:10:45 +08:00
|
|
|
"name": "Jiekou.AI",
|
2025-11-17 19:47:46 +08:00
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Sao10K/L3-8B-Stheno-v3.2",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baichuan/baichuan-m2-32b",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baidu/ernie-4.5-300b-a47b-paddle",
|
|
|
|
|
"tags": "LLM,CHAT,123K",
|
|
|
|
|
"max_tokens": 123000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baidu/ernie-4.5-vl-424b-a47b",
|
|
|
|
|
"tags": "LLM,CHAT,123K",
|
|
|
|
|
"max_tokens": 123000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-5-haiku-20241022",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-5-sonnet-20241022",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-7-sonnet-20250219",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3-haiku-20240307",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-haiku-4-5-20251001",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,20K,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 20000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-1-20250805",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-20250514",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-5-20250929",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,200K,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 200000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-r1-0528",
|
|
|
|
|
"tags": "LLM,CHAT,163K",
|
|
|
|
|
"max_tokens": 163840,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-v3-0324",
|
|
|
|
|
"tags": "LLM,CHAT,163K",
|
|
|
|
|
"max_tokens": 163840,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-v3.1",
|
|
|
|
|
"tags": "LLM,CHAT,163K",
|
|
|
|
|
"max_tokens": 163840,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "doubao-1-5-pro-32k-250115",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "doubao-1.5-pro-32k-character-250715",
|
|
|
|
|
"tags": "LLM,CHAT,200K",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash-20250609",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash-lite",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-lite",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-lite-preview-06-17",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-lite-preview-09-2025",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,1M,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 1048576,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash-preview-05-20",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro-preview-06-05",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-3-12b-it",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "google/gemma-3-27b-it",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-mini",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4.1-nano",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1047576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-codex",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,400K,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 400000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5-pro",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,400K,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 400000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.1",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.1-chat-latest",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.1-codex",
|
|
|
|
|
"tags": "LLM,CHAT,400K",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-3-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4-0709",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4-fast-non-reasoning",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,2M,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 2000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-4-fast-reasoning",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "LLM,2M,IMAGE2TEXT",
|
2025-11-17 19:47:46 +08:00
|
|
|
"max_tokens": 2000000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
2025-11-17 19:47:46 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "grok-code-fast-1",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 256000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gryphe/mythomax-l2-13b",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.1-8b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,16K",
|
|
|
|
|
"max_tokens": 16384,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.2-3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-3.3-70b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "meta-llama/llama-4-scout-17b-16e-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "minimaxai/minimax-m1-80k",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mistral-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mistralai/mistral-nemo",
|
|
|
|
|
"tags": "LLM,CHAT,60K",
|
|
|
|
|
"max_tokens": 60288,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/kimi-k2-0905",
|
|
|
|
|
"tags": "LLM,CHAT,262K",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/kimi-k2-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o1",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o1-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o3",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "o3-mini",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "openai/gpt-oss-120b",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "openai/gpt-oss-20b",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen-2.5-72b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen-mt-plus",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2.5-7b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen2.5-vl-72b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-235b-a22b-fp8",
|
|
|
|
|
"tags": "LLM,CHAT,40K",
|
|
|
|
|
"max_tokens": 40960,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-235b-a22b-instruct-2507",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-235b-a22b-thinking-2507",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-30b-a3b-fp8",
|
|
|
|
|
"tags": "LLM,CHAT,40K",
|
|
|
|
|
"max_tokens": 40960,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-32b-fp8",
|
|
|
|
|
"tags": "LLM,CHAT,40K",
|
|
|
|
|
"max_tokens": 40960,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-8b-fp8",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-coder-480b-a35b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,262K",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-next-80b-a3b-instruct",
|
|
|
|
|
"tags": "LLM,CHAT,65K",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-next-80b-a3b-thinking",
|
|
|
|
|
"tags": "LLM,CHAT,65K",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sao10k/l3-70b-euryale-v2.1",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sao10k/l3-8b-lunaris",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "sao10k/l31-70b-euryale-v2.2",
|
|
|
|
|
"tags": "LLM,CHAT,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "thudm/glm-4.1v-9b-thinking",
|
|
|
|
|
"tags": "LLM,CHAT,65K",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/glm-4.5",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "zai-org/glm-4.5v",
|
|
|
|
|
"tags": "LLM,CHAT,65K",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baai/bge-m3",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-embedding-0.6b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-embedding-8b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32K",
|
|
|
|
|
"max_tokens": 32768,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "baai/bge-reranker-v2-m3",
|
|
|
|
|
"tags": "RE-RANK,8K",
|
|
|
|
|
"max_tokens": 8000,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank"
|
2025-11-17 19:47:46 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen/qwen3-reranker-8b",
|
|
|
|
|
"tags": "RE-RANK,32K",
|
|
|
|
|
"max_tokens": 32768,
|
2026-05-29 17:39:41 +08:00
|
|
|
"model_type": "rerank"
|
2025-11-17 19:47:46 +08:00
|
|
|
}
|
|
|
|
|
]
|
2025-12-09 18:54:14 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "MinerU",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "OCR",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2026-01-09 17:48:45 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "PaddleOCR",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "OCR",
|
|
|
|
|
"status": "1",
|
2026-06-17 14:29:20 +08:00
|
|
|
"url": "https://paddleocr.aistudio-app.com",
|
2026-01-09 17:48:45 +08:00
|
|
|
"llm": []
|
2026-01-19 13:12:42 +08:00
|
|
|
},
|
Feat: add OpenDataLoader PDF parser backend (#14058) (#14097)
### What problem does this PR solve?
Closes #14058.
RAGFlow supports multiple PDF parsing backends (DeepDOC, MinerU,
Docling, TCADP, PaddleOCR). This PR adds **OpenDataLoader**
([opendataloader-project/opendataloader-pdf](https://github.com/opendataloader-project/opendataloader-pdf))
as a new optional backend, giving users a deterministic, local-first
alternative with competitive table extraction accuracy.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
---
### Changes
#### Backend
- `deepdoc/parser/opendataloader_parser.py` — new `OpenDataLoaderParser`
class inheriting `RAGFlowPdfParser`. Implements `check_installation()`
(guards Python package + Java 11+ runtime), `parse_pdf()` with
JSON-first extraction (heading/paragraph/table/list/image/formula) and
Markdown fallback, position-tag generation compatible with the shared
`@@page\tx0\tx1\ty0\ty1##` format, and temp-dir lifecycle with cleanup.
- `rag/app/naive.py` — new `by_opendataloader()` wrapper, registered in
`PARSERS` dict, added to `chunk_token_num=0` override list.
- `rag/flow/parser/parser.py` — `"opendataloader"` branch in the
pipeline PDF handler + check validation list.
#### Infrastructure
- `docker/entrypoint.sh` — `ensure_opendataloader()` function: opt-in
via `USE_OPENDATALOADER=true`, skips gracefully if Java is not on PATH.
#### Frontend
- `web/src/components/layout-recognize-form-field.tsx` —
`OpenDataLoader` added to `ParseDocumentType` enum and parser dropdown.
Cascades automatically to the pipeline editor's Parser component.
#### Docs
- `docs/guides/dataset/select_pdf_parser.md` — added OpenDataLoader
entry and full env-var reference.
---
### Environment variables
| Variable | Default | Description |
|---|---|---|
| `USE_OPENDATALOADER` | `false` | Set `true` to install
`opendataloader-pdf` on container startup |
| `OPENDATALOADER_VERSION` | latest | Pin the PyPI release (e.g.
`==2.2.1`) |
| `OPENDATALOADER_HYBRID` | _(unset)_ | Enable hybrid AI mode (e.g.
`docling-fast`) |
| `OPENDATALOADER_IMAGE_OUTPUT` | _(unset)_ | `off` / `embedded` /
`external` |
| `OPENDATALOADER_OUTPUT_DIR` | _(tmp)_ | Persistent output dir; temp
dir used + cleaned if unset |
| `OPENDATALOADER_DELETE_OUTPUT` | `1` | `0` to retain intermediate
files for debugging |
| `OPENDATALOADER_SANITIZE` | _(unset)_ | `1` to filter prompt-injection
patterns from output |
---
### Dependencies
- **Runtime**: `opendataloader-pdf` (PyPI, Apache 2.0) — opt-in, not
added to `pyproject.toml` core deps. Installed by
`ensure_opendataloader()` at container startup when
`USE_OPENDATALOADER=true`.
- **System**: Java 11+ on PATH (JVM is the underlying engine). The
installer skips with a warning if `java` is not found.
---
### How to test
**Standalone parser:**
```bash
source .venv/bin/activate
uv pip install opendataloader-pdf
python3 -c "
import sys; sys.path.insert(0, '.')
from deepdoc.parser.opendataloader_parser import OpenDataLoaderParser
p = OpenDataLoaderParser()
print('available:', p.check_installation())
s, t = p.parse_pdf('path/to/test.pdf', parse_method='pipeline')
print(f'sections={len(s)} tables={len(t)}')
"
```
### Benchmark vs Docling
```
file parser secs sections tables
----------------------------------------------------------------------
text-heavy.pdf docling 45.29 148 10
text-heavy.pdf opendataloader 3.14 559 0
table-heavy.pdf docling 7.05 76 3
table-heavy.pdf opendataloader 3.71 90 0
complex.pdf docling 42.67 114 8
complex.pdf opendataloader 3.51 180 0
```
2026-04-24 18:33:02 +02:00
|
|
|
{
|
|
|
|
|
"name": "OpenDataLoader",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "OCR",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
|
|
|
|
},
|
2026-01-19 13:12:42 +08:00
|
|
|
{
|
|
|
|
|
"name": "n1n",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
2026-03-12 13:13:06 +08:00
|
|
|
"url": "https://api.n1n.ai/v1",
|
2026-01-19 13:12:42 +08:00
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
|
|
|
|
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-3.5-turbo",
|
|
|
|
|
"tags": "LLM,CHAT,4K",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-chat",
|
|
|
|
|
"tags": "LLM,CHAT,128K",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
}
|
|
|
|
|
]
|
feat: Add Avian as an LLM provider (#13256)
### What problem does this PR solve?
This PR adds [Avian](https://avian.io) as a new LLM provider to RAGFlow.
Avian provides an OpenAI-compatible API with competitive pricing,
offering access to models like DeepSeek V3.2, Kimi K2.5, GLM-5, and
MiniMax M2.5.
**Provider details:**
- API Base URL: `https://api.avian.io/v1`
- Auth: Bearer token via API key
- OpenAI-compatible (chat completions, streaming, function calling)
- Models:
- `deepseek/deepseek-v3.2` — 164K context, $0.26/$0.38 per 1M tokens
- `moonshotai/kimi-k2.5` — 131K context, $0.45/$2.20 per 1M tokens
- `z-ai/glm-5` — 131K context, $0.30/$2.55 per 1M tokens
- `minimax/minimax-m2.5` — 1M context, $0.30/$1.10 per 1M tokens
**Changes:**
- `rag/llm/chat_model.py` — Add `AvianChat` class extending `Base`
- `rag/llm/__init__.py` — Register in `SupportedLiteLLMProvider`,
`FACTORY_DEFAULT_BASE_URL`, `LITELLM_PROVIDER_PREFIX`
- `conf/llm_factories.json` — Add Avian factory with model definitions
- `web/src/constants/llm.ts` — Add to `LLMFactory` enum, `IconMap`,
`APIMapUrl`
- `web/src/components/svg-icon.tsx` — Register SVG icon
- `web/src/assets/svg/llm/avian.svg` — Provider icon
- `docs/references/supported_models.mdx` — Add to supported models table
This follows the same pattern as other OpenAI-compatible providers
(e.g., n1n #12680, TokenPony).
cc @KevinHuSh @JinHai-CN
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
2026-02-27 09:36:55 +00:00
|
|
|
},
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
{
|
|
|
|
|
"name": "Astraflow",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"url": "https://api-us-ca.umodelverse.ai/v1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-7",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-6",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-5-20250929",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-haiku-4-5-20251001",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Max",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Coder",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.6",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-5.1",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.7",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-embedding-8b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-ada-002",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
feat: add FuturMix as model provider (#14419)
## Summary
Add [FuturMix](https://futurmix.ai) as a new model provider. FuturMix is
an OpenAI-compatible unified AI gateway that provides access to 22+
models (GPT, Claude, Gemini, DeepSeek, and more) through a single API
endpoint and key.
- **API Base**: `https://futurmix.ai/v1` (OpenAI-compatible)
- **Supported capabilities**: Chat, Embedding, Image2Text, TTS,
Speech2Text, Rerank
### Changes
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Add `FuturMix` to `SupportedLiteLLMProvider`
enum, `FACTORY_DEFAULT_BASE_URL`, and `LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `FuturMixChat(Base)` — follows
Astraflow/Avian pattern |
| `rag/llm/embedding_model.py` | Add `FuturMixEmbed(OpenAIEmbed)` —
follows Astraflow pattern |
| `rag/llm/cv_model.py` | Add `FuturMixCV(GptV4)` — follows
SILICONFLOW/OpenRouter pattern |
| `rag/llm/tts_model.py` | Add `FuturMixTTS(OpenAITTS)` — follows
CometAPI/DeerAPI pattern |
| `rag/llm/sequence2txt_model.py` | Add `FuturMixSeq2txt(GPTSeq2txt)` —
follows StepFun pattern |
| `rag/llm/rerank_model.py` | Add `FuturMixRerank(OpenAI_APIRerank)` |
| `conf/llm_factories.json` | Add factory config with 8 chat, 2
embedding, 1 image2text, 2 TTS, 1 speech2text models |
| `docs/guides/models/supported_models.mdx` | Add FuturMix to supported
models table |
### Models included
- **Chat**: claude-sonnet-4-20250514, claude-3.5-haiku, gpt-4o,
gpt-4o-mini, gemini-2.5-flash, gemini-2.0-flash, deepseek-chat,
deepseek-reasoner
- **Embedding**: text-embedding-3-small, text-embedding-3-large
- **Image2Text**: gpt-4o
- **TTS**: tts-1, tts-1-hd
- **Speech2Text**: whisper-1
## Test plan
- [ ] Verify FuturMix appears in the model provider list in RAGFlow UI
- [ ] Configure FuturMix with API key and test chat completion
- [ ] Test embedding model with document indexing
- [ ] Test image2text with a sample image
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 10:59:37 +08:00
|
|
|
{
|
|
|
|
|
"name": "FuturMix",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT,SPEECH2TEXT,TTS,TEXT RE-RANK",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"url": "https://futurmix.ai/v1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-20250514",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-3.5-haiku",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.0-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-chat",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek-reasoner",
|
|
|
|
|
"tags": "LLM,CHAT,64k",
|
|
|
|
|
"max_tokens": 65536,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o",
|
2026-06-10 15:35:21 +08:00
|
|
|
"tags": "IMAGE2TEXT,128k",
|
feat: add FuturMix as model provider (#14419)
## Summary
Add [FuturMix](https://futurmix.ai) as a new model provider. FuturMix is
an OpenAI-compatible unified AI gateway that provides access to 22+
models (GPT, Claude, Gemini, DeepSeek, and more) through a single API
endpoint and key.
- **API Base**: `https://futurmix.ai/v1` (OpenAI-compatible)
- **Supported capabilities**: Chat, Embedding, Image2Text, TTS,
Speech2Text, Rerank
### Changes
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Add `FuturMix` to `SupportedLiteLLMProvider`
enum, `FACTORY_DEFAULT_BASE_URL`, and `LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `FuturMixChat(Base)` — follows
Astraflow/Avian pattern |
| `rag/llm/embedding_model.py` | Add `FuturMixEmbed(OpenAIEmbed)` —
follows Astraflow pattern |
| `rag/llm/cv_model.py` | Add `FuturMixCV(GptV4)` — follows
SILICONFLOW/OpenRouter pattern |
| `rag/llm/tts_model.py` | Add `FuturMixTTS(OpenAITTS)` — follows
CometAPI/DeerAPI pattern |
| `rag/llm/sequence2txt_model.py` | Add `FuturMixSeq2txt(GPTSeq2txt)` —
follows StepFun pattern |
| `rag/llm/rerank_model.py` | Add `FuturMixRerank(OpenAI_APIRerank)` |
| `conf/llm_factories.json` | Add factory config with 8 chat, 2
embedding, 1 image2text, 2 TTS, 1 speech2text models |
| `docs/guides/models/supported_models.mdx` | Add FuturMix to supported
models table |
### Models included
- **Chat**: claude-sonnet-4-20250514, claude-3.5-haiku, gpt-4o,
gpt-4o-mini, gemini-2.5-flash, gemini-2.0-flash, deepseek-chat,
deepseek-reasoner
- **Embedding**: text-embedding-3-small, text-embedding-3-large
- **Image2Text**: gpt-4o
- **TTS**: tts-1, tts-1-hd
- **Speech2Text**: whisper-1
## Test plan
- [ ] Verify FuturMix appears in the model provider list in RAGFlow UI
- [ ] Configure FuturMix with API key and test chat completion
- [ ] Test embedding model with document indexing
- [ ] Test image2text with a sample image
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 10:59:37 +08:00
|
|
|
"max_tokens": 128000,
|
2026-06-10 15:35:21 +08:00
|
|
|
"model_type": [
|
|
|
|
|
"image2text",
|
|
|
|
|
"chat"
|
|
|
|
|
],
|
feat: add FuturMix as model provider (#14419)
## Summary
Add [FuturMix](https://futurmix.ai) as a new model provider. FuturMix is
an OpenAI-compatible unified AI gateway that provides access to 22+
models (GPT, Claude, Gemini, DeepSeek, and more) through a single API
endpoint and key.
- **API Base**: `https://futurmix.ai/v1` (OpenAI-compatible)
- **Supported capabilities**: Chat, Embedding, Image2Text, TTS,
Speech2Text, Rerank
### Changes
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Add `FuturMix` to `SupportedLiteLLMProvider`
enum, `FACTORY_DEFAULT_BASE_URL`, and `LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `FuturMixChat(Base)` — follows
Astraflow/Avian pattern |
| `rag/llm/embedding_model.py` | Add `FuturMixEmbed(OpenAIEmbed)` —
follows Astraflow pattern |
| `rag/llm/cv_model.py` | Add `FuturMixCV(GptV4)` — follows
SILICONFLOW/OpenRouter pattern |
| `rag/llm/tts_model.py` | Add `FuturMixTTS(OpenAITTS)` — follows
CometAPI/DeerAPI pattern |
| `rag/llm/sequence2txt_model.py` | Add `FuturMixSeq2txt(GPTSeq2txt)` —
follows StepFun pattern |
| `rag/llm/rerank_model.py` | Add `FuturMixRerank(OpenAI_APIRerank)` |
| `conf/llm_factories.json` | Add factory config with 8 chat, 2
embedding, 1 image2text, 2 TTS, 1 speech2text models |
| `docs/guides/models/supported_models.mdx` | Add FuturMix to supported
models table |
### Models included
- **Chat**: claude-sonnet-4-20250514, claude-3.5-haiku, gpt-4o,
gpt-4o-mini, gemini-2.5-flash, gemini-2.0-flash, deepseek-chat,
deepseek-reasoner
- **Embedding**: text-embedding-3-small, text-embedding-3-large
- **Image2Text**: gpt-4o
- **TTS**: tts-1, tts-1-hd
- **Speech2Text**: whisper-1
## Test plan
- [ ] Verify FuturMix appears in the model provider list in RAGFlow UI
- [ ] Configure FuturMix with API key and test chat completion
- [ ] Test embedding model with document indexing
- [ ] Test image2text with a sample image
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 10:59:37 +08:00
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-small",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tts-1",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "tts-1-hd",
|
|
|
|
|
"tags": "TTS",
|
|
|
|
|
"max_tokens": 4096,
|
|
|
|
|
"model_type": "tts",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "whisper-1",
|
|
|
|
|
"tags": "SPEECH2TEXT",
|
|
|
|
|
"max_tokens": 25000000,
|
|
|
|
|
"model_type": "speech2text",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "jina-reranker-v2-base-multilingual",
|
|
|
|
|
"tags": "RE-RANK,8k",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "rerank",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
feat: Add Astraflow provider support (global + China endpoints) (#14270)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
2026-04-22 15:38:34 +08:00
|
|
|
{
|
|
|
|
|
"name": "Astraflow-CN",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"url": "https://api.modelverse.cn/v1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-7",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-opus-4-6",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-sonnet-4-5-20250929",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "claude-haiku-4-5-20251001",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-mini",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-5.4-nano",
|
|
|
|
|
"tags": "LLM,CHAT,400k",
|
|
|
|
|
"max_tokens": 400000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gpt-4o-mini",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Max",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-Coder",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-32B",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
|
|
|
|
"tags": "LLM,CHAT,131k",
|
|
|
|
|
"max_tokens": 131072,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "kimi-k2.6",
|
|
|
|
|
"tags": "LLM,CHAT,200k",
|
|
|
|
|
"max_tokens": 200000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "glm-5.1",
|
|
|
|
|
"tags": "LLM,CHAT,128k",
|
|
|
|
|
"max_tokens": 128000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2.7",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "MiniMax-M2",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-pro",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "gemini-2.5-flash",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "qwen3-embedding-8b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8192,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-3-large",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "text-embedding-ada-002",
|
|
|
|
|
"tags": "TEXT EMBEDDING,8K",
|
|
|
|
|
"max_tokens": 8191,
|
|
|
|
|
"model_type": "embedding",
|
|
|
|
|
"is_tools": false
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
feat: Add Avian as an LLM provider (#13256)
### What problem does this PR solve?
This PR adds [Avian](https://avian.io) as a new LLM provider to RAGFlow.
Avian provides an OpenAI-compatible API with competitive pricing,
offering access to models like DeepSeek V3.2, Kimi K2.5, GLM-5, and
MiniMax M2.5.
**Provider details:**
- API Base URL: `https://api.avian.io/v1`
- Auth: Bearer token via API key
- OpenAI-compatible (chat completions, streaming, function calling)
- Models:
- `deepseek/deepseek-v3.2` — 164K context, $0.26/$0.38 per 1M tokens
- `moonshotai/kimi-k2.5` — 131K context, $0.45/$2.20 per 1M tokens
- `z-ai/glm-5` — 131K context, $0.30/$2.55 per 1M tokens
- `minimax/minimax-m2.5` — 1M context, $0.30/$1.10 per 1M tokens
**Changes:**
- `rag/llm/chat_model.py` — Add `AvianChat` class extending `Base`
- `rag/llm/__init__.py` — Register in `SupportedLiteLLMProvider`,
`FACTORY_DEFAULT_BASE_URL`, `LITELLM_PROVIDER_PREFIX`
- `conf/llm_factories.json` — Add Avian factory with model definitions
- `web/src/constants/llm.ts` — Add to `LLMFactory` enum, `IconMap`,
`APIMapUrl`
- `web/src/components/svg-icon.tsx` — Register SVG icon
- `web/src/assets/svg/llm/avian.svg` — Provider icon
- `docs/references/supported_models.mdx` — Add to supported models table
This follows the same pattern as other OpenAI-compatible providers
(e.g., n1n #12680, TokenPony).
cc @KevinHuSh @JinHai-CN
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
2026-02-27 09:36:55 +00:00
|
|
|
{
|
|
|
|
|
"name": "Avian",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "deepseek/deepseek-v3.2",
|
|
|
|
|
"tags": "LLM,CHAT,164K",
|
|
|
|
|
"max_tokens": 164000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "moonshotai/kimi-k2.5",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "z-ai/glm-5",
|
|
|
|
|
"tags": "LLM,CHAT,131K",
|
|
|
|
|
"max_tokens": 131000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "minimax/minimax-m2.5",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1000000,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
}
|
|
|
|
|
]
|
2026-03-06 02:37:27 +01:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "RAGcon",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": []
|
2026-03-20 02:47:48 +00:00
|
|
|
},
|
2026-06-07 19:09:36 -10:00
|
|
|
{
|
|
|
|
|
"name": "Xiaomi",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,IMAGE2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"url": "https://api.xiaomimimo.com/v1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mimo-v2.5-pro",
|
|
|
|
|
"tags": "LLM,CHAT,1M",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mimo-v2.5",
|
|
|
|
|
"tags": "LLM,CHAT,1M,IMAGE2TEXT",
|
|
|
|
|
"max_tokens": 1048576,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "mimo-v2-flash",
|
|
|
|
|
"tags": "LLM,CHAT,256K",
|
|
|
|
|
"max_tokens": 262144,
|
|
|
|
|
"model_type": "chat",
|
|
|
|
|
"is_tools": true
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2026-03-20 02:47:48 +00:00
|
|
|
{
|
|
|
|
|
"name": "Perplexity",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "TEXT EMBEDDING",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "pplx-embed-v1-0.6b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "pplx-embed-v1-4b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "pplx-embed-context-v1-0.6b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"llm_name": "pplx-embed-context-v1-4b",
|
|
|
|
|
"tags": "TEXT EMBEDDING,32000",
|
|
|
|
|
"max_tokens": 32000,
|
|
|
|
|
"model_type": "embedding"
|
|
|
|
|
}
|
|
|
|
|
]
|
Feat: Add New API model provider for OpenAI-compatible gateways (#15991)
## Summary
Add support for **"New API"** as a model provider, enabling connection
to [New API](https://github.com/QuantumNous/new-api) /
[one-api](https://github.com/songquanpeng/one-api) compatible gateways
that aggregate multiple LLM backends behind a unified OpenAI-compatible
`/v1` endpoint.
### Features
- **All model types**: Chat, Embedding, Rerank, Image2Text, TTS,
Speech2Text
- **List Models discovery**: `NewAPI(OpenAIAPICompatible)` class in
`model_meta.py` queries the gateway's `/v1/models` to auto-discover
available models via the native `GET /api/v1/providers/<name>/models`
endpoint
- **Model parameter editing**: Pencil icon on each discovered model row
to edit `model_type`, `max_tokens`, and `features` (e.g. tool call
support) before submitting
- **Custom model addition**: "Add Custom Model" button at the bottom of
the List Models dropdown for models not returned by the API
- **Gear icon settings**: Enabled the Settings gear button on provider
instances to manage models on existing instances (viewMode)
- **viewMode credential passthrough**: Fixed List Models in viewMode —
merges `initialValues` credentials when `api_key`/`base_url` fields are
hidden by `hideWhenInstanceExists`
### Changes
**Backend** (8 files):
- `rag/llm/chat_model.py` — `NewAPIChat(Base)` class
- `rag/llm/embedding_model.py` — `NewAPIEmbed(OpenAIEmbed)` class (no
auto `/v1` append)
- `rag/llm/rerank_model.py` — `NewAPIRerank(Base)` class (uses `/rerank`
endpoint)
- `rag/llm/cv_model.py` — `NewAPICv(GptV4)` class
- `rag/llm/tts_model.py` — `NewAPITTS(OpenAITTS)` class
- `rag/llm/sequence2txt_model.py` — `NewAPISeq2txt(GPTSeq2txt)` class
- `rag/llm/model_meta.py` — `NewAPI(OpenAIAPICompatible)` class for List
Models discovery
- `conf/llm_factories.json` — New API factory entry with all model type
tags
**Frontend** (8 files + 1 new SVG):
- `web/src/assets/svg/llm/new-api.svg` — New API logo icon
- `web/src/constants/llm.ts` — `LLMFactory.NewAPI` enum + `IconMap`
entry
- `web/src/components/svg-icon.tsx` — `NewAPI` added to `svgIcons`
-
`web/src/pages/user-setting/setting-model/modal/provider-modal/field-config/local-llm-configs.ts`
— New API `buildLocalConfig`
-
`web/src/pages/user-setting/setting-model/modal/provider-modal/constants.ts`
— `LIST_MODEL_PROVIDERS` includes NewAPI
- `web/src/pages/user-setting/setting-model/components/used-model.tsx` —
Enable Settings gear button
-
`web/src/pages/user-setting/setting-model/modal/provider-modal/hooks/use-list-models-picker.ts`
— viewMode credential merge + model editing state/handlers
-
`web/src/pages/user-setting/setting-model/modal/provider-modal/hooks/use-list-models-options.tsx`
— Pencil edit icon per model row
-
`web/src/pages/user-setting/setting-model/modal/provider-modal/index.tsx`
— `AddCustomModelDialog` import + edit dialog rendering
**Note on Go implementation**: A Go model driver (`NewAPIModel`
delegating to `OpenAIModel`) has been prepared but is deferred until the
Go runtime is enabled in a future release (current v0.26.0 images use
`API_PROXY_SCHEME=python` and do not compile Go binaries). Will submit
as a follow-up PR.
## Related
- Depends on: #15996 (provider instance API improvements — server-side
credential lookup, idempotent `add_model`, security fixes — required for
viewMode gear icon and batch model submission)
## Test plan
- [ ] Add New API provider with api_key and base_url pointing to an
OpenAI-compatible gateway
- [ ] Click "List Models" — should discover and display available models
from `/v1/models`
- [ ] Click pencil icon on a model — should open edit dialog to change
model_type, max_tokens, features
- [ ] Select multiple models and click OK — should add all selected
models
- [ ] Click gear icon on the added instance — should open viewMode with
List Models working
- [ ] In viewMode, select new models including pre-existing ones, click
OK — should succeed (requires #15996)
- [ ] Verify all model types work: create a Chat assistant, Embedding
KB, Rerank setting
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Tim Wang <wanghualoong@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-26 18:47:20 +08:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "New API",
|
|
|
|
|
"logo": "",
|
|
|
|
|
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT,TTS,SPEECH2TEXT",
|
|
|
|
|
"status": "1",
|
|
|
|
|
"llm": [],
|
|
|
|
|
"rank": "885"
|
2024-11-05 13:58:29 +08:00
|
|
|
}
|
2024-07-16 15:19:43 +08:00
|
|
|
]
|
feat: add FuturMix as model provider (#14419)
## Summary
Add [FuturMix](https://futurmix.ai) as a new model provider. FuturMix is
an OpenAI-compatible unified AI gateway that provides access to 22+
models (GPT, Claude, Gemini, DeepSeek, and more) through a single API
endpoint and key.
- **API Base**: `https://futurmix.ai/v1` (OpenAI-compatible)
- **Supported capabilities**: Chat, Embedding, Image2Text, TTS,
Speech2Text, Rerank
### Changes
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Add `FuturMix` to `SupportedLiteLLMProvider`
enum, `FACTORY_DEFAULT_BASE_URL`, and `LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `FuturMixChat(Base)` — follows
Astraflow/Avian pattern |
| `rag/llm/embedding_model.py` | Add `FuturMixEmbed(OpenAIEmbed)` —
follows Astraflow pattern |
| `rag/llm/cv_model.py` | Add `FuturMixCV(GptV4)` — follows
SILICONFLOW/OpenRouter pattern |
| `rag/llm/tts_model.py` | Add `FuturMixTTS(OpenAITTS)` — follows
CometAPI/DeerAPI pattern |
| `rag/llm/sequence2txt_model.py` | Add `FuturMixSeq2txt(GPTSeq2txt)` —
follows StepFun pattern |
| `rag/llm/rerank_model.py` | Add `FuturMixRerank(OpenAI_APIRerank)` |
| `conf/llm_factories.json` | Add factory config with 8 chat, 2
embedding, 1 image2text, 2 TTS, 1 speech2text models |
| `docs/guides/models/supported_models.mdx` | Add FuturMix to supported
models table |
### Models included
- **Chat**: claude-sonnet-4-20250514, claude-3.5-haiku, gpt-4o,
gpt-4o-mini, gemini-2.5-flash, gemini-2.0-flash, deepseek-chat,
deepseek-reasoner
- **Embedding**: text-embedding-3-small, text-embedding-3-large
- **Image2Text**: gpt-4o
- **TTS**: tts-1, tts-1-hd
- **Speech2Text**: whisper-1
## Test plan
- [ ] Verify FuturMix appears in the model provider list in RAGFlow UI
- [ ] Configure FuturMix with API key and test chat completion
- [ ] Test embedding model with document indexing
- [ ] Test image2text with a sample image
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 10:59:37 +08:00
|
|
|
}
|