Gemini 3.1 Flash Lite Image 示例

Generate an image with gemini-3.1-flash-lite-image

curl --request POST \
  --url https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "A single yellow ceramic banana on a matte white background, soft studio lighting, no text."
        }
      ]
    }
  ]
}
'

import requests

url = "https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent"

payload = { "contents": [
        {
            "role": "user",
            "parts": [{ "text": "A single yellow ceramic banana on a matte white background, soft studio lighting, no text." }]
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    contents: [
      {
        role: 'user',
        parts: [
          {
            text: 'A single yellow ceramic banana on a matte white background, soft studio lighting, no text.'
          }
        ]
      }
    ]
  })
};

fetch('https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_IMAGE_DATA"
            }
          }
        ]
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 37,
    "candidatesTokenCount": 1846,
    "totalTokenCount": 1883,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 37
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1680
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-lite-image",
  "responseId": "response_example"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

POST

v1beta

models

gemini-3.1-flash-lite-image:generateContent

Generate an image with gemini-3.1-flash-lite-image

curl --request POST \
  --url https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "A single yellow ceramic banana on a matte white background, soft studio lighting, no text."
        }
      ]
    }
  ]
}
'

import requests

url = "https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent"

payload = { "contents": [
        {
            "role": "user",
            "parts": [{ "text": "A single yellow ceramic banana on a matte white background, soft studio lighting, no text." }]
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    contents: [
      {
        role: 'user',
        parts: [
          {
            text: 'A single yellow ceramic banana on a matte white background, soft studio lighting, no text.'
          }
        ]
      }
    ]
  })
};

fetch('https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_IMAGE_DATA"
            }
          }
        ]
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 37,
    "candidatesTokenCount": 1846,
    "totalTokenCount": 1883,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 37
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1680
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-lite-image",
  "responseId": "response_example"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "<string>"
  }
}

curl 'https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent' \
  -H 'Authorization: Bearer YOUR_YINGTU_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "折纸质感的友好应用图标"}]}],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "1:1", "imageSize": "1K"}
    }
  }'

本次实测响应的核心结构如下：

{
  "candidates": [{
    "content": {"role": "model", "parts": [{
      "inlineData": {"mimeType": "image/png", "data": "BASE64_IMAGE_DATA"}
    }]},
    "finishReason": "STOP"
  }],
  "usageMetadata": {"promptTokenCount": 42, "totalTokenCount": 1162},
  "modelVersion": "gemini-3.1-flash-lite-image",
  "responseId": "response_example"
}

异步调用只更换 URL 后缀。实测提交返回 HTTP 202，第四次查询得到 completed 和同样的 1K PNG 结果。不要根据轮询次数设置固定超时。调用方受反向代理超时限制，或需要在用户离开页面后继续生成时，再选择异步方式；普通服务端工具能够等待完整结果时，同步调用更容易实现和排查。图片编辑沿用相同 endpoint：在提示词 part 后加入来源图片的 inlineData，保留真实 MIME，并继续使用 imageSize: "1K"。读取结果时遍历全部 parts，不要把 PNG 或 parts[0] 写成固定假设。完整字段说明见参数页。

在线测试

本页 OpenAPI 面板固定使用 gemini-3.1-flash-lite-image:generateContent，并预填有效的 1K 请求体。填入开发凭证后，可直接点击 试一试，无需离开示例页。

试一试会真实计费。Mintlify 会在生成的 cURL 中显示已输入的 Key，请勿分享带凭证的截图。

授权

Authorization

string

header

必填

YingTu API key.

请求体

application/json

contents

Message · object[]

必填

Prompt and optional source image.

Minimum array length: 1

Show child attributes

generationConfig

Output settings · object

Show child attributes

响应

Complete Gemini response

candidates

object[]

必填

Show child attributes

usageMetadata

object

Show child attributes

modelVersion

string

The model version that produced the response.

示例:

"gemini-3.1-flash-lite-image"

responseId

string

Provider response identifier.

示例:

"response_example"

createTime

string<date-time>

Creation time when supplied by the selected model channel.

​在线测试

授权

请求体

响应

在线测试