MaaS_Mimo

请求协议

https

Header

参数名	类型	必填	描述
Content-Type	string	是	固定为 application/json
Authorization	string	是	Bearer ${YOUR_AK}

请求 URL

POST

https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions

请求 Body 参数

参数名	字段类型	是否必填	默认值	描述
messages	array	是	-	对话的消息列表。包含 content, role, name 等子属性。
messages.content	string / array	是	-	开发者消息的内容。
messages.role	string	是	-	开发者消息的角色，可选值：developer。
messages.name	string	否	-	参与者的可选名称，为模型提供信息以区分相同角色的参与者。
model	string	是	-	用于生成响应的模型 ID。
frequency_penalty	number / null	否	0	取值范围 [-2.0, 2.0]。正值会根据 token 在已有文本中的出现频率进行惩罚，降低重复可能性。
max_completion_tokens	integer / null	否	32768	对话补全中可以生成的 token 数的上限。 取值范围为 [1, 8192] 所需范围：[1, 131072]
presence_penalty	number / null	否	0	取值范围 [-2.0, 2.0]。正值会根据 token 是否已在文本中出现进行惩罚，增加谈论新主题的可能性。
response_format	object	否	-	一个指定模型必须输出的格式的对象。
response_format.type	string	是	-	所定义的响应格式类型，仅为 text。
stop	string / array / null	否	null	最多 4 个序列，当 API 生成到这些序列时会停止生成。
stream	boolean / null	否	false	若为 true，模型的响应数据会通过 SSE 流式传输到客户端。
thinking	object	否	-	控制模型是否启用思维链。
thinking.type	string	是	enabled	是否启用思维链，可选值：enabled, disabled。
temperature	number	否	1.0	采样温度，介于 0 和 1.5 之间。较高的值使输出更随机，较低的值更确定。
tool_choice	string	否	auto	控制模型如何选择工具。
tools	array	否	-	模型可能调用的工具列表，目前仅支持函数作为工具。
tools.function	object	是	-	用于生成响应的函数工具。
tools.function.name	string	是	-	工具函数的名称，长度限制为 1-64 字符。
tools.function.description	string	否	-	函数功能的描述，供模型判断何时以及如何调用该函数。
tools.function.parameters	object	否	-	函数接受的参数，以 JSON 模式对象的形式描述。
tools.function.strict	boolean	否	false	生成函数调用时是否启用严格的模式遵循。
tools.type	string	是	-	工具类型，目前仅支持 function。
top_p	number	否	0.95	核采样的概率阈值，用于控制模型生成文本的多样性。

调用示例

模型支持路径：MaaS_Mimo_V2.5_20260423 、MaaS_Mimo_V2.5_pro_20260423

/chat/completions

/chat/completions 非流式请求

curl --location --request POST 'https://genaiapi.cloudsway.net/v1/ai/{Your EndpointPath}/chat/completions' \
--header 'Authorization: Bearer ${your AK}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    "max_completion_tokens": 1024
}'

/v1/messages

curl --location --request POST 'http://genaiapi.cloudsway.net/{Your EndpointPath}/v1/messages' \
--header 'Authorization: Bearer ${your AK}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "max_tokens": 128,
    "system": [
      {
        "type": "text",
        "text": "You are a helpful assistant that remembers our conversation.",
        "cache_control": {"type": "ephemeral"}
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "My name is Alex. I work on machine learning.",
            "cache_control": {"type": "ephemeral"}
          }
        ]
      },
      {"role": "user", "content": "What did I say I work on?"}
    ]
  }'

返回示例

{
    "id": "chatcmpl-LnYo0Rzyh3fkDQGmYoETI54W",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! I'm MiMo, an AI assistant created by Xiaomi. I'm here to help answer your questions, provide information, and assist with various tasks to the best of my abilities. Feel free to ask me anything! 😊",
                "reasoning_content": "Hmm, the user asked for a self-introduction. This is a straightforward request with no complex requirements. \n\nI should keep it concise but cover key points: identity, purpose, and availability. Since I'm an AI assistant, I'll mention my developer and core function. \n\nAdding a friendly closing would make it more engaging. No need for extra details unless the user asks follow-up questions. \n\nThe tone should be helpful and approachable, matching how a digital assistant would naturally introduce itself."
            },
            "finish_reason": "stop",
            "native_finish_reason": "stop"
        }
    ],
    "created": 1780036404,
    "model": "MaaS_Mimo_V2.5_20260423",
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 55,
        "completion_tokens": 149,
        "total_tokens": 204,
        "completion_tokens_details": {
            "accepted_prediction_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "reasoning_tokens": 99,
            "rejected_prediction_tokens": 0
        },
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "cached_tokens": 0,
            "image_tokens": 0
        }
    }
}

统一域名访问

/chat/completions

curl --location --request POST 'https://genaiapi.cloudsway.net/v1/chat/completions' \
--header 'Authorization: Bearer ${your AK}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "MaaS_Mimo_V2.5_20260423",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    "max_completion_tokens": 1024
}'

/v1/messages

curl --location --request POST 'https://genaiapi.cloudsway.net/v1/messages' \
--header 'Authorization: Bearer ${your AK}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "MaaS_Mimo_V2.5_20260423",
    "max_tokens": 128,
    "system": [
      {
        "type": "text",
        "text": "You are a helpful assistant that remembers our conversation.",
        "cache_control": {"type": "ephemeral"}
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "My name is Alex. I work on machine learning.",
            "cache_control": {"type": "ephemeral"}
          }
        ]
      },
      {"role": "user", "content": "What did I say I work on?"}
    ]
  }'

返回示例

{
    "id": "4340ec22040848d9ab8d24c2412684dd",
    "type": "message",
    "role": "assistant",
    "content": [
        {
            "type": "text",
            "text": "You said you work on **machine learning**. Nice to meet you, Alex! 😊"
        },
        {
            "type": "thinking",
            "signature": "",
            "thinking": "The user told me their name is Alex and they work on machine learning."
        }
    ],
    "model": "MaaS_Mimo_V2.5_20260423",
    "usage": {
        "input_tokens": 44,
        "output_tokens": 37
    },
    "stop_reason": "end_turn"
}