Responses API 兼容

MiMo 提供兼容 OpenAI Responses API 格式的调用接口，本文将对请求参数、响应结构和代码示例进行说明。

兼容性说明与限制：

本接口对齐 OpenAI Responses API 规范，便于开发者快速适配集成；仅文档说明参数会正常处理，未定义参数会被过滤并可能返回请求异常，具体差异化约束见下文。

不兼容参数：暂不支持 background、previous_response_id、context_management 等字段，请求中携带此类参数会被忽略或触发报错。
推理档位控制：reasoning.effort 控制模型推理：none 关闭思考；low / medium / high 均开启推理，各档位效果一致，暂不区分推理强度。

请求地址

https://api.xiaomimimo.com/v1/responses

请求头

接口支持以下两种认证方式，请选择其中一种添加到请求头中：

方式一：api-key 字段认证，格式：

api-key: $MIMO_API_KEY
Content-Type: application/json

方式二：Authorization: Bearer 认证，格式：

Authorization: Bearer $MIMO_API_KEY
Content-Type: application/json

请求体

Response 对象（非流式输出）

Response chunk 对象（流式输出）

当你创建响应并将 stream 设为 true 时，服务端会在响应生成过程中向客户端推送服务端发送事件（SSE）。

response.created

响应创建时触发的事件。

response.in_progress

响应处于生成中状态时触发。

response.completed

模型响应生成完成时触发。

response.incomplete

响应以未完成状态结束时触发该事件。

response.output_item.added

当新增一条输出项时触发。

response.output_item.done

当某条输出项标记为完成时触发。

response.content_part.added

新增内容片段时触发。

response.content_part.done

内容片段生成完成时触发。

response.output_text.delta

产生增量文本片段时触发。

response.output_text.done

文本内容最终生成完成时触发。

response.function_call_arguments.delta

产生函数调用参数增量片段时触发。

response.function_call_arguments.done

函数调用参数最终生成完成时触发。

response.reasoning_text.delta

推理文本产生增量片段时触发。

response.reasoning_text.done

推理文本生成完成时触发。

curl --location --request POST 'https://api.xiaomimimo.com/v1/responses' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "instructions": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "input": "please introduce yourself",
    "max_output_tokens": 1024,
    "stream": false,
    "reasoning": {
        "effort": "none"
    }
}'

响应

{
    "id": "resp_5fcaac1af26a4b449f30e1eeeaa8c48f",
    "object": "response",
    "created_at": 1782215659,
    "status": "completed",
    "error": null,
    "incomplete_details": null,
    "model": "mimo-v2.5-pro",
    "metadata": null,
    "output": [
        {
            "id": "msg_1fa8f5011ebf47adb158ecf13c99d06c",
            "type": "message",
            "status": "completed",
            "role": "assistant",
            "content": [
                {
                    "type": "output_text",
                    "text": "Hello! I am MiMo, a large language model developed by Xiaomi's LLM Core Team. I'm here to help answer your questions, generate text, and assist with various tasks. How can I assist you today?",
                    "annotations": []
                }
            ]
        }
    ],
    "output_text": "Hello! I am MiMo, a large language model developed by Xiaomi's LLM Core Team. I'm here to help answer your questions, generate text, and assist with various tasks. How can I assist you today?",
    "usage": {
        "input_tokens": 57,
        "input_tokens_details": {},
        "output_tokens": 46,
        "output_tokens_details": {
            "reasoning_tokens": 0
        },
        "total_tokens": 103
    }
}

更新时间 2026 年 06 月 24 日

curl --location --request POST 'https://api.xiaomimimo.com/v1/responses' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "instructions": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "input": "please introduce yourself",
    "max_output_tokens": 1024,
    "stream": false,
    "reasoning": {
        "effort": "none"
    }
}'

响应

{
    "id": "resp_5fcaac1af26a4b449f30e1eeeaa8c48f",
    "object": "response",
    "created_at": 1782215659,
    "status": "completed",
    "error": null,
    "incomplete_details": null,
    "model": "mimo-v2.5-pro",
    "metadata": null,
    "output": [
        {
            "id": "msg_1fa8f5011ebf47adb158ecf13c99d06c",
            "type": "message",
            "status": "completed",
            "role": "assistant",
            "content": [
                {
                    "type": "output_text",
                    "text": "Hello! I am MiMo, a large language model developed by Xiaomi's LLM Core Team. I'm here to help answer your questions, generate text, and assist with various tasks. How can I assist you today?",
                    "annotations": []
                }
            ]
        }
    ],
    "output_text": "Hello! I am MiMo, a large language model developed by Xiaomi's LLM Core Team. I'm here to help answer your questions, generate text, and assist with various tasks. How can I assist you today?",
    "usage": {
        "input_tokens": 57,
        "input_tokens_details": {},
        "output_tokens": 46,
        "output_tokens_details": {
            "reasoning_tokens": 0
        },
        "total_tokens": 103
    }
}