Gemini 3.1 Flash Image examples

Generate an image with gemini-3.1-flash-image

curl --request POST \
  --url https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-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-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-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/jpeg",
              "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-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-image:generateContent

Generate an image with gemini-3.1-flash-image

curl --request POST \
  --url https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-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-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-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/jpeg",
              "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-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>"
  }
}

Generate a 2K asset

curl 'https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-image:generateContent' \
  -H 'Authorization: Bearer YOUR_YINGTU_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "A modern desk lamp photographed for an architecture magazine"}]
    }],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "1:1", "imageSize": "2K"}
    }
  }'

import os
import requests

response = requests.post(
    "https://api.yingtu.ai/v1beta/models/"
    "gemini-3.1-flash-image:generateContent",
    headers={"Authorization": f"Bearer {os.environ['YINGTU_API_KEY']}"},
    json={
        "contents": [{"role": "user", "parts": [
            {"text": "A modern desk lamp photographed for an architecture magazine"}
        ]}],
        "generationConfig": {
            "responseModalities": ["TEXT", "IMAGE"],
            "imageConfig": {"aspectRatio": "1:1", "imageSize": "2K"},
        },
    },
    timeout=180,
)
response.raise_for_status()
result = response.json()

The verified 2K result returned a 2048 × 2048 JPEG:

{
  "candidates": [{
    "content": {
      "role": "model",
      "parts": [{
        "inlineData": {"mimeType": "image/jpeg", "data": "BASE64_IMAGE_DATA"}
      }]
    },
    "finishReason": "STOP",
    "index": 0
  }],
  "usageMetadata": {
    "promptTokenCount": 37,
    "candidatesTokenCount": 1846,
    "totalTokenCount": 1883
  },
  "modelVersion": "gemini-3.1-flash-image",
  "responseId": "response_example"
}

Queue a 1K task

Use the identical body with imageSize: "1K" and the asynchronous suffix. The live task returned HTTP 202, reached in_progress, and completed after four polls with its Gemini response under result.

curl 'https://api.yingtu.ai/v1beta/models/gemini-3.1-flash-image:asyncGenerateContent' \
  -H 'Authorization: Bearer YOUR_YINGTU_API_KEY' \
  -H 'Content-Type: application/json' \
  -d @request.json

Edit without changing the subject

Send the instruction and source bytes as adjacent parts. Scan the returned parts rather than assuming the image is at index zero; one verified edit returned model text before the JPEG.

Test this model online

The embedded OpenAPI operation uses the fixed gemini-3.1-flash-image:generateContent path. Confirm imageSize, enter a development key, and run the request directly on this page.

The selected size determines the billable tier. Mintlify shows the entered key in its generated cURL; do not share authenticated screenshots.

Authorizations

Authorization

string

header

required

YingTu API key.

Body

application/json

contents

Message · object[]

required

Prompt and optional source image.

Minimum array length: 1

Show child attributes

generationConfig

Output settings · object

Show child attributes

Response

Complete Gemini response

candidates

object[]

required

Show child attributes

usageMetadata

object

Show child attributes

modelVersion

string

The model version that produced the response.

Example:

"gemini-3.1-flash-image"

responseId

string

Provider response identifier.

Example:

"response_example"

createTime

string<date-time>

Creation time when supplied by the selected model channel.

​Generate a 2K asset

​Queue a 1K task

​Edit without changing the subject

​Test this model online

Authorizations

Body

Response

Generate a 2K asset

Queue a 1K task

Edit without changing the subject

Test this model online