> ## Documentation Index
> Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt
> Use this file to discover all available pages before exploring further.

# Nano banana2 Generación de imágenes

>  - Compatible con texto a imagen e imagen a imagen, con salida hasta 4K de resolución
- Hasta 14 imágenes de referencia para consistencia de estilo/personaje
- Compatible con proporciones extremas (1:4, 4:1, 1:8, 8:1)
- Mejora integrada con Google Search para una generación de imágenes más realista 

> [!NOTE]
>
> **Aviso de compatibilidad de nombres de modelo**: Esta interfaz también admite el alias `nano-banana-2-ext`, equivalente a `gemini-3.1-flash-image-preview`; ambos son intercambiables y producen los mismos resultados.

```bash cURL theme={null}
# El campo model puede ser "gemini-3.1-flash-image-preview" o el alias compatible "nano-banana-2-ext"
curl --request POST \
  --url https://gccai.heqingsong.uk/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "Cyberpunk cityscape at night with neon lights",
    "size": "16:9",
    "resolution": "2K",
    "n": 1
  }'
```

```python Python theme={null}
import requests

url = "https://gccai.heqingsong.uk/v1/images/generations"

payload = {
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "Cyberpunk cityscape at night with neon lights",
    "size": "16:9",
    "resolution": "2K",
    "n": 1
}

headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript JavaScript theme={null}
const url = "https://gccai.heqingsong.uk/v1/images/generations";

const payload = {
  model: "gemini-3.1-flash-image-preview",
  prompt: "Cyberpunk cityscape at night with neon lights",
  size: "16:9",
  resolution: "2K",
  n: 1
};

const headers = {
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(payload)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));
```

```go Go theme={null}
package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io/ioutil"
    "net/http"
)

func main() {
    url := "https://gccai.heqingsong.uk/v1/images/generations"

    payload := map[string]interface{}{
        "model":      "gemini-3.1-flash-image-preview",
        "prompt":     "Cyberpunk cityscape at night with neon lights",
        "size":       "16:9",
        "resolution": "2K",
        "n":          1,
    }

    jsonData, _ := json.Marshal(payload)

    req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
    req.Header.Set("Authorization", "Bearer <token>")
    req.Header.Set("Content-Type", "application/json")

    client := &http.Client{}
    resp, err := client.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()

    body, _ := ioutil.ReadAll(resp.Body)
    fmt.Println(string(body))
}
```

```java Java theme={null}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;

public class Main {
    public static void main(String[] args) throws Exception {
        String url = "https://gccai.heqingsong.uk/v1/images/generations";

        String payload = """
        {
          "model": "gemini-3.1-flash-image-preview",
          "prompt": "Cyberpunk cityscape at night with neon lights",
          "size": "16:9",
          "resolution": "2K",
          "n": 1
        }
        """;

        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create(url))
            .header("Authorization", "Bearer <token>")
            .header("Content-Type", "application/json")
            .POST(HttpRequest.BodyPublishers.ofString(payload))
            .build();

        HttpResponse<String> response = client.send(request,
            HttpResponse.BodyHandlers.ofString());

        System.out.println(response.body());
    }
}
```

```php PHP theme={null}
<?php

$url = "https://gccai.heqingsong.uk/v1/images/generations";

$payload = [
    "model" => "gemini-3.1-flash-image-preview",
    "prompt" => "Cyberpunk cityscape at night with neon lights",
    "size" => "16:9",
    "resolution" => "2K",
    "n" => 1
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
]);

$response = curl_exec($ch);
curl_close($ch);

echo $response;
?>
```

```ruby Ruby theme={null}
require 'net/http'
require 'json'
require 'uri'

url = URI("https://gccai.heqingsong.uk/v1/images/generations")

payload = {
  model: "gemini-3.1-flash-image-preview",
  prompt: "Cyberpunk cityscape at night with neon lights",
  size: "16:9",
  resolution: "2K",
  n: 1
}

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json

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

```swift Swift theme={null}
import Foundation

let url = URL(string: "https://gccai.heqingsong.uk/v1/images/generations")!

let payload: [String: Any] = [
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "Cyberpunk cityscape at night with neon lights",
    "size": "16:9",
    "resolution": "2K",
    "n": 1
]

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }

    if let data = data, let responseString = String(data: data, encoding: .utf8) {
        print(responseString)
    }
}

task.resume()
```

```csharp C# theme={null}
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://gccai.heqingsong.uk/v1/images/generations";

        var payload = @"{
            ""model"": ""gemini-3.1-flash-image-preview"",
            ""prompt"": ""Cyberpunk cityscape at night with neon lights"",
            ""size"": ""16:9"",
            ""resolution"": ""2K"",
            ""n"": 1
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

```c C theme={null}
#include <stdio.h>
#include <curl/curl.h>

int main(void) {
    CURL *curl;
    CURLcode res;

    curl_global_init(CURL_GLOBAL_DEFAULT);
    curl = curl_easy_init();

    if(curl) {
        const char *url = "https://gccai.heqingsong.uk/v1/images/generations";
        const char *payload = "{"
            "\"model\":\"gemini-3.1-flash-image-preview\","
            "\"prompt\":\"Cyberpunk cityscape at night with neon lights\","
            "\"size\":\"16:9\","
            "\"resolution\":\"2K\","
            "\"n\":1"
        "}";

        struct curl_slist *headers = NULL;
        headers = curl_slist_append(headers, "Authorization: Bearer <token>");
        headers = curl_slist_append(headers, "Content-Type: application/json");

        curl_easy_setopt(curl, CURLOPT_URL, url);
        curl_easy_setopt(curl, CURLOPT_POSTFIELDS, payload);
        curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);

        res = curl_easy_perform(curl);

        if(res != CURLE_OK) {
            fprintf(stderr, "curl_easy_perform() failed: %s\n",
                    curl_easy_strerror(res));
        }

        curl_slist_free_all(headers);
        curl_easy_cleanup(curl);
    }

    curl_global_cleanup();
    return 0;
}
```

```objectivec Objective-C theme={null}
#import <Foundation/Foundation.h>

int main(int argc, const char * argv[]) {
    @autoreleasepool {
        NSURL *url = [NSURL URLWithString:@"https://gccai.heqingsong.uk/v1/images/generations"];

        NSDictionary *payload = @{
            @"model": @"gemini-3.1-flash-image-preview",
            @"prompt": @"Cyberpunk cityscape at night with neon lights",
            @"size": @"16:9",
            @"resolution": @"2K",
            @"n": @1
        };

        NSError *error;
        NSData *jsonData = [NSJSONSerialization dataWithJSONObject:payload
                                                          options:0
                                                            error:&error];

        NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];
        [request setHTTPMethod:@"POST"];
        [request setValue:@"Bearer <token>" forHTTPHeaderField:@"Authorization"];
        [request setValue:@"application/json" forHTTPHeaderField:@"Content-Type"];
        [request setHTTPBody:jsonData];

        NSURLSessionDataTask *task = [[NSURLSession sharedSession]
            dataTaskWithRequest:request
            completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
                if (error) {
                    NSLog(@"Error: %@", error);
                    return;
                }
                NSString *result = [[NSString alloc] initWithData:data
                                                        encoding:NSUTF8StringEncoding];
                NSLog(@"%@", result);
            }];

        [task resume];
        [[NSRunLoop mainRunLoop] run];
    }
    return 0;
}
```

```ocaml OCaml theme={null}
(* Requires cohttp and yojson libraries *)
open Lwt
open Cohttp
open Cohttp_lwt_unix

let url = "https://gccai.heqingsong.uk/v1/images/generations"

let payload = {|{
  "model": "gemini-3.1-flash-image-preview",
  "prompt": "Cyberpunk cityscape at night with neon lights",
  "size": "16:9",
  "resolution": "2K",
  "n": 1
}|}

let () =
  let headers = Header.init ()
    |> fun h -> Header.add h "Authorization" "Bearer <token>"
    |> fun h -> Header.add h "Content-Type" "application/json"
  in
  let body = Cohttp_lwt.Body.of_string payload in

  let response = Client.post ~headers ~body (Uri.of_string url) >>= fun (resp, body) ->
    body |> Cohttp_lwt.Body.to_string >|= fun body_str ->
    print_endline body_str
  in
  Lwt_main.run response
```

```dart Dart theme={null}
import 'dart:convert';
import 'package:http/http.dart' as http;

void main() async {
  final url = Uri.parse('https://gccai.heqingsong.uk/v1/images/generations');

  final payload = {
    'model': 'gemini-3.1-flash-image-preview',
    'prompt': 'Cyberpunk cityscape at night with neon lights',
    'size': '16:9',
    'resolution': '2K',
    'n': 1
  };

  final response = await http.post(
    url,
    headers: {
      'Authorization': 'Bearer <token>',
      'Content-Type': 'application/json',
    },
    body: jsonEncode(payload),
  );

  print(response.body);
}
```

```r R theme={null}
library(httr)
library(jsonlite)

url <- "https://gccai.heqingsong.uk/v1/images/generations"

payload <- list(
  model = "gemini-3.1-flash-image-preview",
  prompt = "Cyberpunk cityscape at night with neon lights",
  size = "16:9",
  resolution = "2K",
  n = 1
)

response <- POST(
  url,
  add_headers(
    Authorization = "Bearer <token>",
    `Content-Type` = "application/json"
  ),
  body = toJSON(payload, auto_unbox = TRUE),
  encode = "raw"
)

cat(content(response, "text"))
```

```json 200 theme={null}
{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01K8SGYNNNVBQTXNR4MM964S7K"
    }
  ]
}
```

```json 400 theme={null}
{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}
```

```json 401 theme={null}
{
  "error": {
    "code": 401,
    "message": "Invalid authentication credentials",
    "type": "authentication_error"
  }
}
```

```json 402 theme={null}
{
  "error": {
    "code": 402,
    "message": "Insufficient balance. Please top up your account",
    "type": "payment_required"
  }
}
```

```json 403 theme={null}
{
  "error": {
    "code": 403,
    "message": "Access forbidden. You don't have permission to access this resource",
    "type": "permission_error"
  }
}
```

```json 429 theme={null}
{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded. Please try again later",
    "type": "rate_limit_error"
  }
}
```

```json 500 theme={null}
{
  "error": {
    "code": 500,
    "message": "Internal server error. Please try again later",
    "type": "server_error"
  }
}
```

```json 502 theme={null}
{
  "error": {
    "code": 502,
    "message": "Bad gateway. The server is temporarily unavailable",
    "type": "bad_gateway"
  }
}
```

## Autorizaciones

**Authorization** `string` *required*

Todos los endpoints de la API requieren autenticación con Bearer Token

Obtenga su API Key:

Visite la [página de gestión de API Keys](https://gccai.heqingsong.uk/keys) para obtener su API Key

Añádala al encabezado de la solicitud:

```
Authorization: Bearer YOUR_API_KEY
```

## Body

**model** `string` *required* (default: gemini-3.1-flash-image-preview)

Nombre del modelo de generación de imágenes

Modelos compatibles:

* `gemini-3.1-flash-image-preview` - Versión estándar (alias compatible `nano-banana-2-ext`)
* `gemini-3.1-flash-image-preview-official` - Versión oficial (alias compatible `nano-banana-2`)

Ejemplo: `"gemini-3.1-flash-image-preview"` o `"gemini-3.1-flash-image-preview-official"`

> [!NOTE]
>
> Para mantener la compatibilidad con llamadas anteriores, los alias `nano-banana-2-ext` (corresponde a `gemini-3.1-flash-image-preview`) y `nano-banana-2` (corresponde a `gemini-3.1-flash-image-preview-official`) siguen estando disponibles.

**nsfw\_check** `boolean` (default: false)

Indica si se debe moderar el contenido antes de enviar la tarea de imagen.

* `true`: revisar los prompts y las imágenes de entrada con `omni-moderation-latest`
* `false` u omitido: no enviar una solicitud de moderación, sin coste ni latencia de moderación adicionales (predeterminado)

**prompt** `string` *required*

Descripción textual para la generación de la imagen

**size** `string`

Proporción de la imagen

Proporciones compatibles:

* `auto` - Elige automáticamente la proporción
* `1:1` - Cuadrada, avatares, redes sociales
* `3:2` / `2:3` - Fotografías estándar
* `4:3` / `3:4` - Proporción de pantalla tradicional
* `16:9` / `9:16` - Pantalla panorámica / portadas de video vertical
* `5:4` / `4:5` - Imágenes de Instagram
* `21:9` - Banner ultra panorámico
* `1:4` / `4:1` - Póster largo / banner
* `1:8` / `8:1` - Imágenes extremadamente largas / banners publicitarios

> [!WARNING]
>
> En texto a imagen, cuando `size` es `auto`, el valor predeterminado es `1:1` o `16:9`; en imagen a imagen, la proporción sigue la respuesta del upstream. Se recomienda especificar una proporción.

**resolution** `string` (default: 1K)

Resolución de la imagen de salida

Valores compatibles:

* `0.5K` - \~512px, vista previa de baja resolución
* `1K` - \~1024px, resolución estándar (predeterminado)
* `2K` - \~2048px, alta resolución
* `4K` - \~4096px, resolución ultra alta

> **Nota:** Las diferentes resoluciones tienen precios distintos. 4K cuesta más que 1K.

**n** `integer`

Número de imágenes a generar

Rango: 1

Predeterminado: 1

**⚠️ Nota:** Debe introducirse como número puro (p. ej., `1`), no use comillas o se producirá un error

**official\_fallback** `boolean` (default: false)

Si se debe usar el canal oficial como fallback

* `false`: No usar (predeterminado)
* `true`: Usar el canal oficial

> [!WARNING]
>
> Cuando se usa el canal oficial (`gemini-3.1-flash-image-preview-official`), este parámetro no puede usarse.

**image\_urls** `array`

Lista de URLs de imágenes de referencia para generación de imagen a imagen

Se admiten dos formatos:

**1. URL completa de la imagen**

* URL de imagen accesible públicamente (http\:// o https\://)
* Ejemplo: `https://example.com/image.jpg`

**2. Formato codificado en Base64**

* **Debe usar el formato completo Data URI**
* Formato: `data:image/{format};base64,{base64data}`
* Formatos de imagen compatibles: jpeg, png, webp
* Ejemplo: `data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEAYABg...`
* ⚠️ Nota: Debe incluir el prefijo `data:image/jpeg;base64,`

**Limitaciones:**

* Máximo **14** imágenes de referencia (recomendado: hasta 10 referencias de objeto + 4 de personaje)
* Tamaño por imagen: no debe superar 10MB
* Formatos compatibles: jpeg, png, webp

**google\_search** `boolean` (default: false)

Activar la mejora con búsqueda de texto de Google

* `true`: El modelo buscará información textual en la web para asistir la generación de la imagen, útil en escenarios que requieran información del mundo real
* `false`: Desactivado (predeterminado)

**google\_image\_search** `boolean` (default: false)

Activar la mejora con búsqueda de imágenes de Google

* `true`: Además de la búsqueda de texto, también buscará imágenes de referencia para asistir la generación, útil en escenarios que requieran referencias visuales
* `false`: Desactivado (predeterminado)

> **Nota:** Debe usarse junto con `google_search: true`

## Response

**code** `integer`

Código de estado de la respuesta

**data** `array`

Array de datos de la respuesta

**Propiedades**

**status** `string`

Estado de la tarea

* `submitted` - Enviada

**task\_id** `string`

Identificador único de la tarea


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.