视频识别

POST

{{url}}/v1beta/models/gemini-2.5-flash:generateContent

最后修改时间：2025-11-29 15:45:47

Gemini支持小于20MB的视频base64文件直接传输识别，目前暂不支持超出20MB的视频文件识别，如需建议使用直连Key。

请求参数

Query 参数

Header 参数

Body 参数application/json

示例

{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "总结视频内容"
                },
                {
                    "inline_data": {
                        "mime_type": "video/mp4",
                        "data": "'$VIDEO_B64'"
                    }
                }
            ]
        }
    ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location -g --request POST 'http://api.example.com/v1beta/models/gemini-2.5-flash:generateContent?key=sk-xxx' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "总结视频内容"
                },
                {
                    "inline_data": {
                        "mime_type": "video/mp4",
                        "data": "'\''$VIDEO_B64'\''"
                    }
                }
            ]
        }
    ]
}'

返回响应

🟢200成功

application/json

Body

示例

{
    "candidates": [
        {
            "content": {
                "role": "model",
                "parts": [
                    {
                        "text": "视频开始时，两只小象在泥泞的地面上嬉戏。一只站立的小象用鼻子和身体推着另一只躺在泥水中的小象，后者在泥水中快乐地打滚。随后，躺着的小象慢慢起身，两只小象都沾满了泥巴。它们互相靠近，并在泥水中玩耍，其中一只小象还用鼻子吸水并喷洒。它们继续在泥泞的水坑中移动，最后慢慢走出画面。"
                    }
                ]
            },
            "finishReason": "STOP",
            "avgLogprobs": -3.20458740234375
        }
    ],
    "usageMetadata": {
        "promptTokenCount": 11298,
        "candidatesTokenCount": 100,
        "totalTokenCount": 12256,
        "trafficType": "ON_DEMAND",
        "promptTokensDetails": [
            {
                "modality": "AUDIO",
                "tokenCount": 975
            },
            {
                "modality": "TEXT",
                "tokenCount": 3
            },
            {
                "modality": "VIDEO",
                "tokenCount": 10320
            }
        ],
        "candidatesTokensDetails": [
            {
                "modality": "TEXT",
                "tokenCount": 100
            }
        ],
        "thoughtsTokenCount": 858
    },
    "modelVersion": "gemini-2.5-flash",
    "createTime": "2025-11-29T15:43:12.048354Z",
    "responseId": "kBQraeL5AsqE998P26jViQY"
}

修改于 2025-11-29 15:45:47

图像识别

普通对话