元景万悟智能体平台模型导入样例大全（实时更新中～）
万物平台作为可支持多种 AI 模型导入的统一平台，其模型导入功能对开发者而言意义重大。本文将为大家详细介绍，该平台支持的一系列供应商，包括 OpenAI-API-compatible、联通元景、Ollama、通义千问、火山引擎等。同时，平台还支持 LLM、rerank、embedding 类型的模型导入。为了方便各位开发者判断所导入的模型是否被平台支持，本文会将所有的 http 请求一一列举出来，
·
元景万悟智能体平台模型导入样例大全目录
引言
元景万悟智能体平台作为可支持多种 AI 模型导入的统一平台，其模型导入功能对开发者而言意义重大。本文将为大家详细介绍，该平台支持的一系列供应商（包括 OpenAI-API-compatible、联通元景、Ollama、通义千问、火山引擎、百度千帆等）提供的LLM、rerank、embedding 等多种模型类型的模型导入方式。
为了方便各位开发者判断所导入的模型是否被平台支持，本文会将所有的 http 请求一一列举出来，供大家参考使用。
LLM
OpenAI-API- compatible
curl --location 'URL' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer api-key' \
--data '{
"messages": [
{
"role": "user",
"content": "你是谁"
}
],
"model": "glm-4.7",
"stream": false
}'
非流式响应
{
"id": "5c89fcf81a3d46799703cc52c3953220",
"object": "chat.completion",
"created": 1779673020,
"model": "glm-4.7",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好！很高兴见到你。我是GLM，一个由Z.ai训练的大语言模型。\n\n有什么我能帮助你的问题或者你想了解的话题吗？无论是工作学习上的疑问，还是日常生活中的好奇，我都很乐意为你提供帮助。",
"reasoning_content": "收到用户发来的\"你好\"这个简单问候。这是一个常见的开场白，用户可能是在测试我的反应，或者准备开始一段对话。\n\n我需要友好地回应，并表达出乐于提供帮助的态度。考虑到用户使用中文交流，我应该用中文回应。回应要简洁友好，同时为后续对话留出空间。\n\n用户没有提供具体的上下文或问题，所以我不需要做复杂的分析。保持自然、友好的语气就好。可以简单问候一下，然后询问有什么可以帮助的。"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 6,
"completion_tokens": 152,
"total_tokens": 158,
"completion_tokens_details": {
"reasoning_tokens": 103
}
}
}
流式响应
data: {"id":"02d24f2e357d4c9d90f7e62909a43c3c","object":"chat.completion.chunk","created":1779673082,"model":"glm-4.7","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":null,"tool_calls":null},"logprobs":null,"finish_reason":null,"matched_stop":null}],"usage":null}
data: {"id":"02d24f2e357d4c9d90f7e62909a43c3c","object":"chat.completion.chunk","created":1779673082,"model":"glm-4.7","choices":[{"index":0,"delta":{"role":null,"content":null,"reasoning_content":"收到","tool_calls":null},"logprobs":null,"finish_reason":null,"matched_stop":null}],"usage":null}
联通元景
curl --location 'https://maas.ai-yuanjing.com/openapi/compatible-mode/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer api-key' \
--data '{
"messages": [
{
"content": "你好",
"role": "user"
}
],
"model": "glm-4.7",
"stream": true
}'
非流式响应
{
"id": "4c37cabb66e94f499df9d34f62d13d13",
"object": "chat.completion",
"created": 1779673263,
"model": "glm-4.7",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好！很高兴见到你。我是GLM，Z.ai训练的大语言模型。\n\n今天我能为你做些什么？无论是回答问题、提供信息，还是进行日常交流，我都很乐意帮助你。",
"reasoning_content": "收到用户发来的\"你好\"这样简单的问候，需要礼貌地回应并引导对话。首先，应该以友好的方式回应用户的问候，比如使用\"你好！\"来匹配对方的语气。然后，考虑到用户可能需要帮助或想开始某个话题，应该主动询问有什么可以协助的，比如\"有什么我可以帮助你的吗？\"或者\"请问有什么问题需要解答吗？\"这样既保持了对话的开放性，又鼓励用户进一步表达他们的需求。同时，要注意使用自然、流畅的语言，避免过于机械或生硬的表达，确保回应符合中文的交流习惯和文化背景。最后，检查是否有拼写或语法错误，保持回应的准确性和专业性。"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 6,
"completion_tokens": 181,
"total_tokens": 187,
"completion_tokens_details": {
"reasoning_tokens": 140
}
}
}
流式响应
data: {"id":"02d24f2e357d4c9d90f7e62909a43c3c","object":"chat.completion.chunk","created":1779673082,"model":"glm-4.7","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":null,"tool_calls":null},"logprobs":null,"finish_reason":null,"matched_stop":null}],"usage":null}
data: {"id":"02d24f2e357d4c9d90f7e62909a43c3c","object":"chat.completion.chunk","created":1779673082,"model":"glm-4.7","choices":[{"index":0,"delta":{"role":null,"content":null,"reasoning_content":"收到","tool_calls":null},"logprobs":null,"finish_reason":null,"matched_stop":null}],"usage":null}
Ollam
curl --location 'http://ip:11434/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-oss:120b-cloud",
"messages": [
{
"role": "user",
"content": "你好"
}
],
"stream": false
}'
非流式响应
{
"id": "chatcmpl-736",
"object": "chat.completion",
"created": 1779673684,
"model": "gpt-oss:120b-cloud",
"system_fingerprint": "fp_ollama",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好！有什么我可以帮助你的吗？😊",
"reasoning": "We need to respond in Chinese, greeting. Probably ask how can help."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 68,
"completion_tokens": 35,
"total_tokens": 103
}
}
流式响应
data: {"id":"chatcmpl-779","object":"chat.completion.chunk","created":1779673885,"model":"gpt-oss:120b-cloud","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"The"},"finish_reason":null}]}
data: {"id":"chatcmpl-779","object":"chat.completion.chunk","created":1779673885,"model":"gpt-oss:120b-cloud","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" user"},"finish_reason":null}]}
通义千问
curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header 'Authorization: Bearer api-key' \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-flash",
"messages": [
{
"role": "user",
"content": "你好"
}
],
"stream": false,
"enable_thinking":true
}'
非流式响应
{
"choices": [
{
"message": {
"content": "你好！😊 有什么我可以帮你的吗？",
"reasoning_content": "嗯，用户发来“你好”，这是一个常见的打招呼方式。我需要友好地回应。首先，确认用户可能需要帮助，所以应该用中文回复，保持礼貌。\n\n接下来，考虑用户可能的意图。他们可能刚接触这个平台，或者有具体的问题需要解决。作为AI，我应该提供帮助，同时保持简洁。\n\n检查之前的对话历史，但这里没有上下文，所以需要从头开始。确保回复不带任何假设，避免复杂信息。\n\n可能需要询问用户需要什么帮助，这样能引导他们进一步说明需求。例如，“你好！有什么我可以帮你的吗？”\n\n还要注意语气，用表情符号可能让回复更亲切，但不确定用户偏好，所以可能保持中性。不过根据之前的例子，有时候用😊可以增加友好感。\n\n避免使用专业术语，保持口语化。比如不要说“请问您需要什么帮助？”，而是更自然的“你好！有什么我可以帮你的吗？”\n\n检查有没有拼写错误，确保回复正确。中文的“你好”是正确的。\n\n可能需要考虑用户是否是第一次使用，所以回复要友好且开放，鼓励他们提出问题。\n\n最后，确保回复简短，不要冗长，这样用户不会感到压力。\n\n所以，综合起来，回复应该是：“你好！😊 有什么我可以帮你的吗？” 这样既友好又明确。",
"role": "assistant"
},
"finish_reason": "stop",
"index": 0,
"logprobs": null
}
],
"object": "chat.completion",
"usage": {
"prompt_tokens": 9,
"completion_tokens": 292,
"total_tokens": 301
},
"created": 1754966125,
"system_fingerprint": null,
"model": "qwen-flash",
"id": "chatcmpl-ae34fd13-c4c1-987d-bc20-09fe6f6d4936"
}
流式响应
data: {"model":"qwen3-max-2026-01-23","id":"chatcmpl-3d616dd0-7ac5-9470-bf7c-8c4949764168","created":1779673968,"object":"chat.completion.chunk","usage":null,"choices":[{"logprobs":null,"index":0,"delta":{"content":"","role":"assistant","reasoning_content":""},"finish_reason":null}]}
data: {"model":"qwen3-max-2026-01-23","id":"chatcmpl-3d616dd0-7ac5-9470-bf7c-8c4949764168","choices":[{"delta":{"content":"","reasoning_content":"We"},"index":0,"finish_reason":null,"logprobs":null}],"created":1779673968,"object":"chat.completion.chunk","usage":null}
火山引擎
curl --location 'https://ark.cn-beijing.volces.com/api/v3/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer api-key' \
--data '{
"do_sample": false,
"messages": [
{
"content": "你好",
"role": "user"
}
],
"model": "doubao-seed-1-6-flash-250715",
"repetition_penalty": 1.1,
"stream": true,
"temperature": 0.01
}'
非流式响应
{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "你好呀！很高兴见到你~ 有什么我可以帮你的吗？😊",
"reasoning_content": "\n用户现在说“你好”，我需要友好地回应。首先，保持礼貌和热情，直接回应用户的问候，然后可以稍微引导一下，问问用户有什么需要帮助的，这样能让对话继续下去。比如可以说“你好呀！很高兴见到你~ 有什么我可以帮你的吗？😊” 这样既回应了问候，又表达了愿意提供帮助的态度，还带了个表情符号显得更亲切。",
"role": "assistant"
}
}
],
"created": 1754966401,
"id": "021754966399956ef34c300eb7cd27671b96789a585234f4250fd",
"model": "doubao-seed-1-6-flash-250715",
"service_tier": "default",
"object": "chat.completion",
"usage": {
"completion_tokens": 119,
"prompt_tokens": 85,
"total_tokens": 204,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 101
}
}
}
流式响应
data: {"choices":[{"delta":{"content":"","reasoning_content":"用户","role":"assistant"},"index":0}],"created":1779674048,"id":"021779674047654ec2a974ffc08eb8a410ac7a7438c004933cbf5","model":"doubao-seed-2-0-mini-260215","service_tier":"default","object":"chat.completion.chunk","usage":null}
data: {"choices":[{"delta":{"content":"","reasoning_content":"说","role":"assistant"},"index":0}],"created":1779674048,"id":"021779674047654ec2a974ffc08eb8a410ac7a7438c004933cbf5","model":"doubao-seed-2-0-mini-260215","service_tier":"default","object":"chat.completion.chunk","usage":null}
百度千帆
curl --location --request POST 'https://qianfan.baidubce.com/v2/chat/completions' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "ernie-x1.1",
"messages": [
{
"role": "user",
"content": "你好啊"
}
],
"enable_thinking": true
}'
非流式响应
{
"id": "as-xjvaidygax",
"object": "chat.completion",
"created": 1779674086,
"model": "ernie-x1.1",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好！很高兴见到你。今天有什么想聊的或者需要帮忙的吗？无论是生活琐事、学习问题还是其他话题，我都很乐意倾听和提供帮助。",
"reasoning_content": "用户现在说“你好啊”，我需要回应。首先，用户可能是在进行友好的问候，我应该以友好的态度回复。根据系统提示，我是文心X1.1，需要深入分析用户需求并给出满足需求的回复。用户这里只是简单的问候，所以回复应该友好且自然，不需要深入分析。\n\n首先，我应该回应问候，比如“你好！”然后可以加入一些友好的内容，比如询问用户今天过得怎么样，或者表达愿意帮助的意愿。需要避免重复系统设定中的内容，比如不提到竞品或其他无关信息。\n\n需要确保回复符合文心X1.1的定位，即基于飞桨框架研发，能够处理复杂需求，但这里用户只是问候，所以回复应简洁友好。同时，要避免使用竞品相关的词汇，比如不提到DeepSeek、OpenAI等。\n\n总结下来，回复应该包括：友好的问候，可能的话加入一些互动内容，比如询问用户情况，或者表达愿意提供帮助的意愿。需要保持自然，不涉及系统设定中的敏感信息。"
},
"finish_reason": "stop",
"flag": 0
}
],
"usage": {
"prompt_tokens": 1,
"completion_tokens": 238,
"total_tokens": 239,
"completion_tokens_details": {
"reasoning_tokens": 206
}
}
}
流式响应
data: {"id":"as-ai01tnk6m2","object":"chat.completion.chunk","created":1779674416,"model":"ernie-x1.1","choices":[{"index":0,"delta":{"content":null,"role":"assistant","reasoning_content":"用户"},"flag":0}]}
data: {"id":"as-ai01tnk6m2","object":"chat.completion.chunk","created":1779674416,"model":"ernie-x1.1","choices":[{"index":0,"delta":{"content":null,"reasoning_content":"现在"},"flag":0}]}
无问芯穹（停止对个人提供模型服务）
curl --location --request POST 'https://cloud.infini-ai.com/maas/v1/chat/completions' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "deepseek-v3.2",
"messages": [
{
"role": "user",
"content": "你是谁"
}
],
"enable_thinking": false
}'
非流式响应
{
"id": "as-e5tr6wpbes",
"object": "chat.completion",
"created": 1774403310,
"model": "deepseek-v3.2",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "我是DeepSeek，由深度求索公司创造的AI助手！😊\n\n我是一个纯文本模型，虽然不支持多模态识别功能，但我有文件上传功能，可以帮你处理图像、txt、pdf、ppt、word、excel等文件，并从中读取文字信息进行分析处理。我完全免费使用，拥有128K的上下文长度，还支持联网搜索功能（需要你在Web/App中手动点开联网搜索按键）。\n\n你可以通过官方应用商店下载我的App来使用我。有什么问题或者需要帮助的地方，尽管告诉我，我会热情细致地为你解答！✨"
},
"finish_reason": "stop",
"flag": 0
}
],
"usage": {
"prompt_tokens": 11,
"completion_tokens": 121,
"total_tokens": 132
}
}
流式响应
{
"choices": [
{
"delta": {
"content": "😊",
"role": "assistant"
},
"index": 0
}
],
"created": 1754966363,
"id": "021754966363144ef34c300eb7cd27671b96789a585234fa38263",
"model": "doubao-seed-1-6-flash-250715",
"service_tier": "default",
"object": "chat.completion.chunk",
"usage": null
}
DeepSeek
curl --location --request POST 'https://api.deepseek.com/v1/chat/completions' \
--header 'Authorization: Bearer apikey' \
--header 'Host: api.deepseek.com' \
--header 'Connection: keep-alive' \
--data-raw '{
"model": "deepseek-v4-flash",
"thinking": {
"type": "enabled"
},
"messages": [
{
"role": "user",
"content": "你好啊!"
}
],
"stream": false
}'
非流式响应
{
"id": "bf4b2502-0609-4216-a523-35a384f9024d",
"object": "chat.completion",
"created": 1779675157,
"model": "deepseek-v4-flash",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好呀！😊 很高兴见到你！\n\n有什么我可以帮你的吗？无论是闲聊、解答问题，还是需要一些建议，我都很乐意陪你聊聊～",
"reasoning_content": "好的，用户打了个招呼，问“你好啊!”。这是一个非常简单的开场问候。用户可能只是开始对话，或者想测试我是否在线。深层需求可能是建立连接，开启一个友好的对话氛围。不需要复杂处理，直接热情回应问候，并主动提供帮助，引导对话继续。可以用开放式问题邀请用户提出具体需求。"
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 7,
"completion_tokens": 104,
"total_tokens": 111,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 70
},
"prompt_cache_hit_tokens": 0,
"prompt_cache_miss_tokens": 7
},
"system_fingerprint": "fp_8b330d02d0_prod0820_fp8_kvcache_20260402"
}
流式响应
data: {"id":"daee64aa-e2c8-4b8b-abf5-a98a8a116606","object":"chat.completion.chunk","created":1779675247,"model":"deepseek-v4-flash","system_fingerprint":"fp_8b330d02d0_prod0820_fp8_kvcache_20260402","choices":[{"index":0,"delta":{"content":"的吗","reasoning_content":null},"logprobs":null,"finish_reason":null}]}
data: {"id":"daee64aa-e2c8-4b8b-abf5-a98a8a116606","object":"chat.completion.chunk","created":1779675247,"model":"deepseek-v4-flash","system_fingerprint":"fp_8b330d02d0_prod0820_fp8_kvcache_20260402","choices":[{"index":0,"delta":{"content":"？","reasoning_content":null},"logprobs":null,"finish_reason":null}]}
data: {"id":"daee64aa-e2c8-4b8b-abf5-a98a8a116606","object":"chat.completion.chunk","created":1779675247,"model":"deepseek-v4-flash","system_fingerprint":"fp_8b330d02d0_prod0820_fp8_kvcache_20260402","choices":[{"index":0,"delta":{"content":"","reasoning_content":null},"logprobs":null,"finish_reason":"stop"}],"usage":{"prompt_tokens":7,"completion_tokens":142,"total_tokens":149,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens_details":{"reasoning_tokens":104},"prompt_cache_hit_tokens":0,"prompt_cache_miss_tokens":7}}
data: [DONE]
智谱
curl --location --request POST 'https://open.bigmodel.cn/api/paas/v4/chat/completions' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "glm-4.5-flash",
"messages": [
{
"role": "user",
"content": "say hi"
}
],
"max_tokens": 1024
}'
非流式响应
{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hi! 👋 How can I help you today?",
"reasoning_content": "\nWe are going to respond with a friendly greeting.\n Since the user said \"say hi\", we can respond with a simple \"Hi!\" or a more enthusiastic greeting.\n Let's go with a warm and friendly response.",
"role": "assistant"
}
}
],
"created": 1779675566,
"id": "20260525101923d7e2dc165c8a42b5",
"model": "glm-4.5-flash",
"object": "chat.completion",
"request_id": "20260525101923d7e2dc165c8a42b5",
"usage": {
"completion_tokens": 58,
"completion_tokens_details": {
"reasoning_tokens": 44
},
"prompt_tokens": 7,
"prompt_tokens_details": {
"cached_tokens": 6
},
"total_tokens": 65
}
}
流式响应
data: {"id":"20260525102057bea67ca8276a4f4d","created":1779675657,"object":"chat.completion.chunk","model":"glm-4.5-flash","choices":[{"index":0,"delta":{"role":"assistant","content":" today"}}]}
data: {"id":"20260525102057bea67ca8276a4f4d","created":1779675657,"object":"chat.completion.chunk","model":"glm-4.5-flash","choices":[{"index":0,"delta":{"role":"assistant","content":"?"}}]}
data: {"id":"20260525102057bea67ca8276a4f4d","created":1779675657,"object":"chat.completion.chunk","model":"glm-4.5-flash","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7,"completion_tokens":48,"total_tokens":55,"prompt_tokens_details":{"cached_tokens":2},"completion_tokens_details":{"reasoning_tokens":33}}}
data: [DONE]
Text-Rerank
OpenAI-API- compatible
curl --location 'URL' \
--header 'Authorization: Bearer api-key' \
--header 'Content-Type: application/json' \
--data '{
"model": "模型id",
"query": "Apple",
"documents": [
"你好啊，世界",
"我爱吃汉堡",
"尖尖我噶奶",
"乌萨奇",
"雷欧奥特曼"
],
"top_n": 2,
"return_documents": true
}'
响应
{
"model": "jina-reranker-v2-base-multilingual",
"usage": {
"total_tokens": 42
},
"results": [
{
"index": 3,
"document": {
"text": "乌萨奇"
},
"relevance_score": 0.9674102663993835
},
{
"index": 0,
"document": {
"text": "你好啊，世界"
},
"relevance_score": 0.16132023930549622
},
{
"index": 1,
"document": {
"text": "我爱吃汉堡"
},
"relevance_score": 0.06853749603033066
}
]
}
联通元景
curl --location --request POST 'https://maas-api.ai-yuanjing.com/openapi/v1/yuanjing/reranker' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model":"qwen3-reranker-0.6b",
"instruction": "Given a web search query, retrieve relevant passages that answer the query",
"query": "今天天气不错",
"top_n":1,
"documents": [
"天气很好",
"股票涨跌跟天气无关",
"今天北京雾霾严重"
]
}'
响应
{
"id": "rerank-bff1ac559120e8db",
"lid": "35b9c1d2-6045-4aa7-a569-fa7d9a5d3a54",
"model": "qwen3-reranker-0.6b",
"results": [
{
"document": null,
"index": 0,
"relevance_score": 0.9184987545013428
}
],
"usage": {
"prompt_tokens": 24,
"total_tokens": 24
}
}
通义千问
curl --location 'https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank' \
--header 'Authorization: Bearer api-key' \
--header 'Content-Type: application/json' \
--data '{
"model": "gte-rerank",
"input":{
"query": "什么是文本排序模型",
"documents": [
"文本排序模型广泛用于搜索引擎和推荐系统中，它们根据文本相关性对候选文本进行排序",
"量子计算是计算科学的一个前沿领域",
"预训练语言模型的发展给文本排序模型带来了新的进展"
]
},
"parameters": {
"return_documents": true,
"top_n": 3
}
}'
响应
{
"output": {
"results": [
{
"document": {
"text": "文本排序模型广泛用于搜索引擎和推荐系统中，它们根据文本相关性对候选文本进行排序"
},
"index": 0,
"relevance_score": 0.7315062086803763
},
{
"document": {
"text": "预训练语言模型的发展给文本排序模型带来了新的进展"
},
"index": 2,
"relevance_score": 0.5831720487049298
},
{
"document": {
"text": "量子计算是计算科学的一个前沿领域"
},
"index": 1,
"relevance_score": 0.04973238644524712
}
]
},
"usage": {
"total_tokens": 79
},
"request_id": "8baa31dc-a786-9326-8e20-895c74bbff16"
}
Jina
curl --location --request POST 'https://api.jina.ai/v1/rerank' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "jina-reranker-v3",
"query": "乌萨奇",
"top_n": 3,
"documents": [
"你好啊，世界",
"我爱吃汉堡",
"尖尖我噶奶",
"乌萨奇",
"雷欧奥特曼"
],
"return_documents": true
}'
响应
{
"model": "jina-reranker-m0",
"object": "list",
"usage": {
"total_tokens": 944
},
"results": [
{
"index": 0,
"relevance_score": 0.95689275
},
{
"index": 2,
"relevance_score": 0.58661758
},
{
"index": 1,
"relevance_score": 0.54053584,
"document": {
"text": "数据提取么？为什么不用正则啊，你用正则不就全解决了么？"
}
}
]
}
百度千帆
curl --location --request POST 'https://qianfan.baidubce.com/v2/rerank' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "bce-reranker-base",
"query": "上海天气",
"documents": [
"上海气候",
"北京美食",
"新疆天气",
"威海天气"
]
}'
响应
{
"id": "as-njdrrv27ba",
"object": "reranker_list",
"created": 1775633269,
"model": "bce-reranker-base",
"results": [
{
"document": "上海气候",
"relevance_score": 0.689619243144989,
"index": 0
},
{
"document": "威海天气",
"relevance_score": 0.5348251461982727,
"index": 3
},
{
"document": "新疆天气",
"relevance_score": 0.5021781921386719,
"index": 2
},
{
"document": "北京美食",
"relevance_score": 0.36954259872436523,
"index": 1
}
],
"usage": {
"prompt_tokens": 18,
"total_tokens": 18
}
}
智谱
curl --location --request POST 'https://open.bigmodel.cn/api/paas/v4/rerank' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "rerank",
"query": "查询候选文本A",
"documents": [
"需要打分的候选文本A",
"需要打分的候选文本B"
],
"return_documents": true,
"top_n": 1
}'
响应
{
"created": 1779676250,
"id": "2026052510305053147a493ac34288",
"request_id": "2026052510305053147a493ac34288",
"results": [
{
"document": "需要打分的候选文本A",
"index": 0,
"relevance_score": 1.0
}
],
"usage": {
"completion_tokens": 0,
"prompt_tokens": 94,
"total_tokens": 94
}
}
Multimodal-Rerank
联通元景
curl --location --request POST 'https://maas-api.ai-yuanjing.com/openapi/v1/yuanjing/reranker' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "qwen3-vl-reranker-2b",
"return_documents": true,
"query": {
"content": [
{
"type": "text",
"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."
}
]
},
"documents": {
"content": [
{
"type": "text",
"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."
},
{
"type": "image_url",
"image_url": {
"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
}
}
]
}
}'
响应
{
"id": "rerank-87f00f4f3a30c2a8",
"lid": "48960c00-deba-4d84-9c8a-0c9eda68f300",
"model": "qwen3-vl-reranker-2b",
"results": [
{
"document": {
"multi_modal": {
"image_url": {
"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
},
"type": "image_url"
},
"text": null
},
"index": 1,
"relevance_score": 0.8397780060768127
},
{
"document": {
"multi_modal": {
"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.",
"type": "text"
},
"text": null
},
"index": 0,
"relevance_score": 0.6214891076087952
}
],
"usage": {
"prompt_tokens": 1493,
"total_tokens": 1493
}
}
通义千问
curl --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "qwen3-vl-rerank",
"input": {
"query": {
"text": "图片的天气如何"
},
"documents": [
{
"text": "阳光明媚晴天"
},
{
"image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/tower.png"
},
{
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"
}
]
},
"parameters": {
"return_documents": true,
"fps": 1.0
}
}'
响应
{
"output": {
"results": [
{
"document": {
"image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/tower.png"
},
"index": 1,
"relevance_score": 0.7966751446706077
},
{
"document": {
"text": "阳光明媚晴天"
},
"index": 0,
"relevance_score": 0.7523324273803708
},
{
"document": {
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"
},
"index": 2,
"relevance_score": 0.6586620581826317
}
]
},
"usage": {
"image_tokens": 1776,
"input_tokens": 196,
"total_tokens": 1972
},
"request_id": "64707b28-5ac6-9d2f-a378-7c7ed8c3f171"
}
Jina
curl --location --request POST 'https://api.jina.ai/v1/rerank' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "jina-reranker-m0",
"query": "苹果",
"return_documents": true,
"documents": [
{
"image": "https://gips1.baidu.com/it/u=3874647369,3220417986&fm=3028&app=3028&f=JPEG&fmt=auto?w=720&h=1280"
},
{
"text": "数据提取么？为什么不用正则啊，你用正则不就全解决了么？"
}
]
}'
响应
{
"model": "jina-reranker-m0",
"object": "list",
"usage": {
"total_tokens": 763
},
"results": [
{
"index": 0,
"relevance_score": 0.80415996
},
{
"index": 1,
"relevance_score": 0.62025366,
"document": {
"text": "数据提取么？为什么不用正则啊，你用正则不就全解决了么？"
}
}
]
}
Text-Embedding
OpenAI-API- compatible
curl --location 'URL' \
--header 'Authorization: Bearer api-key' \
--header 'Content-Type: application/json' \
--data '{
"model": "BAAI/bge-large-zh-v1.5",
"input": [
"风急天高猿啸哀",
"渚清沙白鸟飞回"
],
"encoding_format": "float"
}'
响应
{
"object": "list",
"data": [
{
"embedding": [
0.018213777,
-0.026578045,
0.018492958,
-0.01139059,
0.04650041,
0.021854298,
-0.056059573,
-0.034439784,
0.043842606,
……
],
"index": 1,
"object": "embedding"
}
],
"model": "BAAI/bge-large-zh-v1.5",
"usage": {
"prompt_tokens": 18,
"completion_tokens": 0,
"total_tokens": 18
}
}
联通元景
curl --location 'https://maas-api.ai-yuanjing.com/openapi/compatible-mode/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer api-key' \
--data '{
"model": "qwen3-embed-0.6b",
"input": [
" 你好"
],
"encoding_format": "float"
}'
响应
{
"id": "embd-15c7e7b5-eccf-9140-afe2-42e25e88fd6d",
"object": "list",
"created": 1754967486,
"model": "qwen3-embed-0.6b",
"data": [
{
"object": "embedding",
"embedding": [
0.013916015625,
0.0147705078125,
0.06689453125,
……
],
"index": 0
}
],
"usage": {
"prompt_tokens": 3,
"completion_tokens": 0,
"total_tokens": 3
}
}
Ollama
curl --location 'http://ip:11434/v1/embeddings' \
--header 'Content-Type: application/json' \
--data '{
"encoding_format": "float",
"input": [
" 你好"
],
"model": "granite-embedding:latest"
}'
响应
{
"object": "list",
"data": [
{
"object": "embedding",
"embedding": [
0.011519907,
-0.14500324,
0.092740096,
……
],
"index": 0
}
],
"model": "granite-embedding:latest",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}
通义千问
curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings' \
--header 'Authorization: Bearer api-key' \
--header 'Content-Type: application/json' \
--data '{
"encoding_format": "float",
"input": [
"你好"
],
"model": "text-embedding-v4"
}'
响应
{
"data": [
{
"embedding": [
0.00904093962162733,
0.040408216416835785,
-0.025859294459223747,
0.03675258532166481,
0.04067809507250786,
……
],
"index": 0,
"object": "embedding"
}
],
"object": "list",
"model": "text-embedding-v4",
"usage": {
"prompt_tokens": 2,
"total_tokens": 2
},
"id": "21fe5ad3-c5b7-9ba4-bad2-9d926691b4f3"
}
Jina
curl --location --request POST 'https://api.jina.ai/v1/embeddings' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "jina-embeddings-v3",
"input": [
"针对敏感肌专门设计的天然有机护肤产品：体验由芦荟和洋甘菊提取物带来的自然呵护。我们的护肤产品特别为敏感肌设计，温和滋润，保护您的肌肤不受刺激。让您的肌肤告别不适，迎来健康光彩。"
]
}'
响应
{
"model": "jina-embeddings-v3",
"object": "list",
"usage": {
"total_tokens": 149
},
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.04124837,
-0.01002589,
0.03389473,
-0.04472601,
0.06938843,
……
0.0232379
]
}
]
}
百度千帆
curl --location --request POST 'https://qianfan.baidubce.com/v2/embeddings' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "embedding-v1",
"input": [
"A man is eating pasta.",
"yes"
]
}'
响应
{
"id": "as-9ehk1rjrf5",
"object": "list",
"created": 1775633417,
"data": [
{
"object": "embedding",
"embedding": [
0.1443854570388794,
0.006749877706170082,
……,
0,
0
],
"index": 0
},
{
"object": "embedding",
"embedding": [
0.03906888887286186,
0.016539443284273148,
……,
0,
0
],
"index": 1
}
],
"model": "embedding-v1",
"usage": {
"prompt_tokens": 7,
"total_tokens": 7
}
}
智谱
curl --location --request POST 'https://open.bigmodel.cn/api/paas/v4/embeddings' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "embedding-3",
"input": "你好，今天天气怎么样.",
"dimensions": 16
}'
响应
{
"data": [
{
"embedding": [
-0.027951399,
0.0953701,
-0.08269339,
0.00012156474,
0.020286415,
0.09308534,
-0.06095137,
0.0060527585,
-0.0070108813,
-0.032041848,
0.024082055,
-0.0078031756,
-0.045031786,
-0.021318238,
0.022092108,
0.03821437
],
"index": 0,
"object": "embedding"
}
],
"model": "embedding-3",
"object": "list",
"usage": {
"completion_tokens": 0,
"prompt_tokens": 10,
"total_tokens": 10
}
}
火山引擎
curl --location --request POST 'https://ark.cn-beijing.volces.com/api/v3/embeddings' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"input": [
"你好",
"ni"
],
"model": "doubao-embedding-large-text-250515"
}'
响应
{
"created": 1779676614,
"id": "021779676613904f411679b62b940c17675a12ff8d6ef7c973969",
"data": [
{
"embedding": [
-0.4609375,
0.6953125,
0.6953125,
-0.443359375,
-0.20703125,
-0.02490234375,
-2.40625,
-0.15234375,
1.578125,
-0.294921875
],
"index": 0,
"object": "embedding"
},
{
"embedding": [
-0.4609375,
0.6953125,
0.6953125,
-0.443359375,
-0.20703125,
-0.02490234375,
-2.40625,
-0.15234375,
1.578125,
-0.294921875
],
"index": 1,
"object": "embedding"
}
],
"model": "doubao-embedding-large-text-250515",
"object": "list",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}
Multimodal-Embedding
联通元景
curl --location --request POST 'https://maas-api.ai-yuanjing.com/openapi/compatible-mode/v1/embeddings' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "qwen3-vl-embedding-2b",
"input": [
{
"image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/tower.png"
}
]
}'
响应
{
"id": "embd-b334cdc6c0004c3fa65c438785342f3d",
"object": "list",
"created": 1779678476,
"model": "qwen3-vl-embedding-2b",
"data": [
{
"object": "embedding",
"embedding": [
-0.03401639685034752,
-0.030026819556951523,
0.018478043377399445,
……，
-0.029186908155679703
],
"index": 0
}
],
"usage": {
"prompt_tokens": 439,
"completion_tokens": 0,
"total_tokens": 439
}
}
通义千问
curl --silent --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/embeddings/multimodal-embedding/multimodal-embedding' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "tongyi-embedding-vision-plus",
"input": {
"contents": [
{"text": "多模态向量模型"},
{"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
{"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"}
]
}
}'
响应
{
"output": {
"embeddings": [
{
"index": 0,
"embedding": [
-0.026611328125,
-0.016571044921875,
-0.02227783203125,
...
],
"type": "text"
},
{
"index": 1,
"embedding": [
0.051544189453125,
0.007717132568359375,
0.026611328125,
...
],
"type": "image"
},
{
"index": 2,
"embedding": [
-0.0217437744140625,
-0.016448974609375,
0.040679931640625,
...
],
"type": "video"
}
]
},
"usage": {
"input_tokens": 10,
"input_tokens_details": {
"image_tokens": 896,
"text_tokens": 7
},
"output_tokens": 3,
"total_tokens": 906
},
"request_id": "1fff9502-a6c5-9472-9ee1-73930fdd04c5"
}
Jina
curl https://api.jina.ai/v1/embeddings \
-H "Authorization: Bearer apikey" \
--data-raw '{
{
"model": "jina-embeddings-v5-omni-small",
"task": "retrieval.query",
"normalized": true,
"input": [
{
"text": "A beautiful sunset over the beach"
},
{
"text": "Un beau coucher de soleil sur la plage"
},
{
"text": "海滩上美丽的日落"
},
{
"text": "浜辺に沈む美しい夕日"
},
{
"image": "https://i.ibb.co/nQNGqL0/beach1.jpg"
},
{
"image": "https://i.ibb.co/r5w8hG8/beach2.jpg"
},
{
"image": "iVBORw0KGgoAAAANSUhEUgAAABwAAAA4CAIAAABhUg/jAAAAMklEQVR4nO3MQREAMAgAoLkoFreTiSzhy4MARGe9bX99lEqlUqlUKpVKpVKpVCqVHksHaBwCA2cPf0cAAAAASUVORK5CYII="
}
]
}'
响应
{
"model": "jina-embeddings-v5-omni-small",
"object": "list",
"usage": {
"total_tokens": 883,
"prompt_tokens": 883,
"image_tokens": 842
},
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.00685768,
-0.00982197,
-0.06087854,
0.02619193,
0.08600864,
...
]
},
{
"object": "embedding",
"index": 1,
"embedding": [
0.0167022,
-0.03809908,
-0.06500317,
-0.00066865,
0.10111604,
...
]
},
{
"object": "embedding",
"index": 2,
"embedding": [
-0.00001888,
-0.00049144,
-0.06216438,
0.02368167,
0.07585534,
...
]
},
{
"object": "embedding",
"index": 3,
"embedding": [
0.0084498,
0.0156442,
-0.06721211,
0.03978648,
0.09888679,
...
]
},
{
"object": "embedding",
"index": 4,
"embedding": [
-0.05217391,
0.00525784,
-0.07886752,
0.01076845,
0.10920119,
...
]
},
{
"object": "embedding",
"index": 5,
"embedding": [
-0.05041899,
-0.01312994,
-0.08361149,
0.00892836,
0.10125814,
...
]
},
{
"object": "embedding",
"index": 6,
"embedding": [
-0.01788215,
0.0469248,
-0.10095174,
-0.00989226,
0.18364084,
...
]
}
]
}
ASR（同步）
通义千问
curl --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Authorization: Bearer apikey' \
--data-raw '{
"model": "qwen3-asr-flash",
"input": {
"messages": [
{
"content": [
{
"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
}
],
"role": "user"
}
]
}
}'
响应
{
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"annotations": [
{
"emotion": "neutral",
"language": "zh",
"type": "audio_info"
}
],
"content": [
{
"text": "欢迎使用阿里云。"
}
],
"role": "assistant"
}
}
]
},
"usage": {
"audio_tokens": 42,
"input_tokens": 42,
"input_tokens_details": {
"audio_tokens": 42,
"text_tokens": 0
},
"output_tokens": 12,
"output_tokens_details": {
"text_tokens": 12
},
"seconds": 1,
"total_tokens": 54
},
"request_id": "5bcef799-d659-99bb-9c39-5db846bfb173"
}
火山引擎
curl --location --request POST 'https://openspeech.bytedance.com/api/v3/auc/bigmodel/recognize/flash' \
--header 'X-Api-App-Key: apikey' \
--header 'X-Api-Access-Key: access-key' \
--header 'X-Api-Resource-Id: volc.bigasr.auc_turbo' \
--header 'X-Api-Request-Id: 67ee89ba-7050-4c04-a3d7-ac61a63499b3' \
--header 'X-Api-Sequence: -1' \
--data-raw '{
"audio": {
"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
}
}'
响应
{
"audio_info": {
"duration": 1696
},
"result": {
"additions": {
"duration": "1696"
},
"text": "换英语使用阿里云。",
"utterances": [
{
"end_time": 1400,
"start_time": 80,
"text": "换英语使用阿里云。",
"words": [
{
"confidence": 0,
"end_time": 120,
"start_time": 80,
"text": "换"
},
{
"confidence": 0,
"end_time": 280,
"start_time": 240,
"text": "英"
},
{
"confidence": 0,
"end_time": 440,
"start_time": 360,
"text": "语"
},
{
"confidence": 0,
"end_time": 640,
"start_time": 520,
"text": "使"
},
{
"confidence": 0,
"end_time": 760,
"start_time": 640,
"text": "用"
},
{
"confidence": 0,
"end_time": 960,
"start_time": 880,
"text": "阿"
},
{
"confidence": 0,
"end_time": 1080,
"start_time": 1040,
"text": "里"
},
{
"confidence": 0,
"end_time": 1400,
"start_time": 1280,
"text": "云"
}
]
}
]
}
}
OCR
联通元景
curl --location 'https://maas-api.ai-yuanjing.com/openapi/v1/unicom-ocr' \
--header 'Content-Type: multipart/form-data' \
--header 'Authorization: Bearer api-key' \
--form 'file=上传文件'
响应
{
"code": 0,
"message": "success",
"version": "20240904",
"timestamp": "2026-05-09 02:12:18.205220",
"id": "fa05ee5fc027a92f1459635bac0627c225e77350",
"sha1": "67cef7fe50dfab0fbe292f1c6afbcaf6b21e615f",
"time_cost": 1134.068250656128,
"filename": "",
"data": [
{
"page_num": [
0
],
"type": "text",
"text": "元景-PDF文档解析测试文件",
"length": 14
},
{
"page_num": [
0
],
"type": "text",
"text": "欢迎使用万物智能体开发平台",
"length": 13
},
{
"page_num": [
0
],
"type": "text",
"text": "1",
"length": 1
}
]
}
GUI
联通元景
#!/bin/bash
# 将图像转换为 Base64 编码
image_file="screen_1.png"
image_base64=$(base64 "$image_file" | tr -d '\n')
base64 "$image_file" > image_base64.txt
cat <<EOF > request.json
{
"algo": "gui_agent_v1",
"platform": "Mobile",
"current_screenshot_xml": "",
"current_screenshot": "data:image/jpeg;base64,${image_base64}",
"current_screenshot_width": 720,
"current_screenshot_height": 1280,
"task": "打开百度地图导航到长话大楼",
"history": []
}
EOF
curl https://maas-gz-api.ai-yuanjing.com/openapi/v1/lmm_gui_agent -X POST -H "Content-Type: application/json" -d @request.json -H "Authorization:Bearer $API_TOKEN"
响应
{
"code": 0,
"content": {
"action": "WAIT",
"box": [],
"description": "等待GUI界面加载",
"operation": "WAIT(info='等待GUI界面加载')",
"sensitivity": "<<一般操作>>",
"value": ""
},
"message": "success",
"usage": {
"completion_tokens": 88,
"prompt_tokens": 40,
"total_tokens": 128
}
}
中国智能体开发者社区，聚焦智能体与大模型开发，提供前沿资讯、实用工具链、开源项目及行业案例。通过技术沙龙、开发者大赛等活动，促进经验交流与协作，助力开发者快速构建创新智能应用。
更多推荐
2
0- 0
已为社区贡献1条内容
所有评论(0)