Gemini Native (Image)

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": [
        "TEXT",
        "IMAGE"
      ],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "A cute orange kitten sitting in a garden"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "2K"
        }
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    contents: [
      {
        role: "user",
        parts: [
          {
            text: "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    generationConfig: {
      responseModalities: [
        "TEXT",
        "IMAGE"
      ],
      imageConfig: {
        aspectRatio: "16:9",
        imageSize: "2K"
      }
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'contents' => [
            [
                'role' => 'user',
                'parts' => [
                    [
                        'text' => 'A cute orange kitten sitting in a garden'
                    ]
                ]
            ]
        ],
        'generationConfig' => [
            'responseModalities' => [
                'TEXT',
                'IMAGE'
            ],
            'imageConfig' => [
                'aspectRatio' => '16:9',
                'imageSize' => '2K'
            ]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "contents": []interface{}{
            map[string]interface{}{
                "role": "user",
                "parts": []interface{}{
                    map[string]interface{}{
                        "text": "A cute orange kitten sitting in a garden",
                    },
                },
            },
        },
        "generationConfig": map[string]interface{}{
            "responseModalities": []string{
                "TEXT",
                "IMAGE",
            },
            "imageConfig": map[string]interface{}{
                "aspectRatio": "16:9",
                "imageSize":   "2K",
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "contents": [
            {
                "role": "user",
                "parts": [
                    {
                        "text": "A cute orange kitten sitting in a garden"
                    }
                ]
            }
        ],
        "generationConfig": {
            "responseModalities": [
                "TEXT",
                "IMAGE"
            ],
            "imageConfig": {
                "aspectRatio": "16:9",
                "imageSize": "2K"
            }
        }
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  contents: [
    {
      role: 'user',
      parts: [
        {
          text: 'A cute orange kitten sitting in a garden'
        }
      ]
    }
  ],
  generationConfig: {
    responseModalities: [
      'TEXT',
      'IMAGE'
    ],
    imageConfig: {
      aspectRatio: '16:9',
      imageSize: '2K'
    }
  }
}.to_json

response = http.request(request)
puts response.body

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAAAAQAAAAECAIA..."
            }
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAACAAAAAgACAIA..."
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 13,
    "candidatesTokenCount": 1680,
    "totalTokenCount": 1693,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 13
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1680
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-image",
  "createTime": "2026-06-24T02:41:32.820834Z",
  "responseId": "3EM7auKMMvmTmecP2dTdsAE"
}

POST

models

{model}

:generateContent

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": [
        "TEXT",
        "IMAGE"
      ],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "A cute orange kitten sitting in a garden"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "2K"
        }
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    contents: [
      {
        role: "user",
        parts: [
          {
            text: "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    generationConfig: {
      responseModalities: [
        "TEXT",
        "IMAGE"
      ],
      imageConfig: {
        aspectRatio: "16:9",
        imageSize: "2K"
      }
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'contents' => [
            [
                'role' => 'user',
                'parts' => [
                    [
                        'text' => 'A cute orange kitten sitting in a garden'
                    ]
                ]
            ]
        ],
        'generationConfig' => [
            'responseModalities' => [
                'TEXT',
                'IMAGE'
            ],
            'imageConfig' => [
                'aspectRatio' => '16:9',
                'imageSize' => '2K'
            ]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "contents": []interface{}{
            map[string]interface{}{
                "role": "user",
                "parts": []interface{}{
                    map[string]interface{}{
                        "text": "A cute orange kitten sitting in a garden",
                    },
                },
            },
        },
        "generationConfig": map[string]interface{}{
            "responseModalities": []string{
                "TEXT",
                "IMAGE",
            },
            "imageConfig": map[string]interface{}{
                "aspectRatio": "16:9",
                "imageSize":   "2K",
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "contents": [
            {
                "role": "user",
                "parts": [
                    {
                        "text": "A cute orange kitten sitting in a garden"
                    }
                ]
            }
        ],
        "generationConfig": {
            "responseModalities": [
                "TEXT",
                "IMAGE"
            ],
            "imageConfig": {
                "aspectRatio": "16:9",
                "imageSize": "2K"
            }
        }
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  contents: [
    {
      role: 'user',
      parts: [
        {
          text: 'A cute orange kitten sitting in a garden'
        }
      ]
    }
  ],
  generationConfig: {
    responseModalities: [
      'TEXT',
      'IMAGE'
    ],
    imageConfig: {
      aspectRatio: '16:9',
      imageSize: '2K'
    }
  }
}.to_json

response = http.request(request)
puts response.body

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAAAAQAAAAECAIA..."
            }
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAACAAAAAgACAIA..."
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 13,
    "candidatesTokenCount": 1680,
    "totalTokenCount": 1693,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 13
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1680
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-image",
  "createTime": "2026-06-24T02:41:32.820834Z",
  "responseId": "3EM7auKMMvmTmecP2dTdsAE"
}

Introduction

Nano Banana maps to Google Gemini’s native image generation capability, including Nano Banana (gemini-2.5-flash-image), Nano Banana 2 (gemini-3.1-flash-image, gemini-3.1-flash-image-preview), and Nano Banana Pro (gemini-3-pro-image). When calling the MixRoute native API, use the endpoint POST /v1/models/<model>:generateContent and pass a JSON Payload that follows the Gemini native structure. It supports text-to-image, image-to-image, and multi-image fusion. For complete parameters and multi-model details, see Image generation.

Authentication

Bearer Token, such as Bearer sk-xxxxxxxxxx

Supported Models

Model ID	Description
`gemini-2.5-flash-image`	Nano Banana, cost-effective text-to-image/image-to-image, with fixed 1024px-class output dimensions
`gemini-3.1-flash-image`	Nano Banana 2, an excellent balance of image quality and speed, supporting 1K, 2K, and 4K output
`gemini-3.1-flash-image-preview`	Nano Banana 2 preview, supports image generation testing
`gemini-3-pro-image`	Nano Banana Pro, higher image quality and strong detail control, supporting 1K, 2K, and 4K output

Basic Examples

Text-to-image
Image-to-image

curl -X POST "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "A cute orange kitten sitting in a garden, bright sunshine, high-quality photography"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": [
        "TEXT",
        "IMAGE"
      ],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

curl -X POST "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Generate an image overlooking Canton Tower based on this image"
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAA..."
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": [
        "TEXT",
        "IMAGE"
      ],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

Request Parameters

string

required

The Gemini native (image) model identifier, located in the URL path, such as gemini-3.1-flash-image or gemini-3-pro-image.

array

required

Native conversation or image content list.

Show contents subfields

string

Role identifier, usually "user".

array

required

Content block list. Each element can be a text prompt ({"text": "..."}) or inline media data ({"inlineData": {"mimeType": "...", "data": "<BASE64>"}}).

Show parts subfields

object

Inline media data object.

Show inlineData subfields

string

The MIME format of the media type, such as "image/png", "image/jpeg", "image/webp", and so on.

string

The Base64-encoded image data string (without a prefix).

object

Generation configuration parameters.

Show generationConfig subfields

array

Response modalities. If this field is provided, it must include "IMAGE"; the common form is ["TEXT", "IMAGE"].

object

Image generation configuration.

Show imageConfig subfields

string

The output image aspect ratio. gemini-2.5-flash-image and gemini-3-pro-image support "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", and "21:9"; the gemini-3.1-flash-image series additionally supports "1:4", "4:1", "1:8", and "8:1".

string

The output resolution or size tier. gemini-2.5-flash-image does not use this field and returns fixed 1024px-class dimensions according to the aspect ratio; the gemini-3.1-flash-image series and gemini-3-pro-image support "1K", "2K", and "4K".

For more parameters and model differences, see Image generation.

Response Format

The API returns a JSON response. Images are embedded in candidates as one or more Base64-encoded inlineData entries:

Field	Type	Description
`candidates[].content.parts[].inlineData.mimeType`	string	Image MIME type, such as `image/png`
`candidates[].content.parts[].inlineData.data`	string	Base64-encoded image data
`candidates[].finishReason`	string	Generation finish reason, such as `"STOP"`
`usageMetadata.promptTokenCount`	integer	Number of input tokens
`usageMetadata.candidatesTokenCount`	integer	Number of output tokens (image tokens)
`modelVersion`	string	The actual model version used
`createTime`	string	Generation time (ISO 8601)
`responseId`	string	Unique response identifier

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": [
        "TEXT",
        "IMAGE"
      ],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "A cute orange kitten sitting in a garden"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "2K"
        }
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    contents: [
      {
        role: "user",
        parts: [
          {
            text: "A cute orange kitten sitting in a garden"
          }
        ]
      }
    ],
    generationConfig: {
      responseModalities: [
        "TEXT",
        "IMAGE"
      ],
      imageConfig: {
        aspectRatio: "16:9",
        imageSize: "2K"
      }
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'contents' => [
            [
                'role' => 'user',
                'parts' => [
                    [
                        'text' => 'A cute orange kitten sitting in a garden'
                    ]
                ]
            ]
        ],
        'generationConfig' => [
            'responseModalities' => [
                'TEXT',
                'IMAGE'
            ],
            'imageConfig' => [
                'aspectRatio' => '16:9',
                'imageSize' => '2K'
            ]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "contents": []interface{}{
            map[string]interface{}{
                "role": "user",
                "parts": []interface{}{
                    map[string]interface{}{
                        "text": "A cute orange kitten sitting in a garden",
                    },
                },
            },
        },
        "generationConfig": map[string]interface{}{
            "responseModalities": []string{
                "TEXT",
                "IMAGE",
            },
            "imageConfig": map[string]interface{}{
                "aspectRatio": "16:9",
                "imageSize":   "2K",
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "contents": [
            {
                "role": "user",
                "parts": [
                    {
                        "text": "A cute orange kitten sitting in a garden"
                    }
                ]
            }
        ],
        "generationConfig": {
            "responseModalities": [
                "TEXT",
                "IMAGE"
            ],
            "imageConfig": {
                "aspectRatio": "16:9",
                "imageSize": "2K"
            }
        }
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-3.1-flash-image:generateContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  contents: [
    {
      role: 'user',
      parts: [
        {
          text: 'A cute orange kitten sitting in a garden'
        }
      ]
    }
  ],
  generationConfig: {
    responseModalities: [
      'TEXT',
      'IMAGE'
    ],
    imageConfig: {
      aspectRatio: '16:9',
      imageSize: '2K'
    }
  }
}.to_json

response = http.request(request)
puts response.body

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAAAAQAAAAECAIA..."
            }
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAACAAAAAgACAIA..."
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 13,
    "candidatesTokenCount": 1680,
    "totalTokenCount": 1693,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 13
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1680
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-image",
  "createTime": "2026-06-24T02:41:32.820834Z",
  "responseId": "3EM7auKMMvmTmecP2dTdsAE"
}

Gemini Text Embedding (embedContent)Image Generation

Popular Models

Smart Routing

OpenAI SDK Usage

Text Series

Embedding Series

Image Series

Video Series

Others

Introduction

Authentication

Supported Models

Basic Examples

Request Parameters

Response Format

​Introduction

​Authentication

​Supported Models

​Basic Examples

​Request Parameters

​Response Format

Introduction

Authentication

Supported Models

Basic Examples

Request Parameters

Response Format