curl --request POST \
--url https://api.evolink.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "nano-banana-beta",
"prompt": "A cat playing on the grass"
}
'import requests
url = "https://api.evolink.ai/v1/images/generations"
payload = {
"model": "nano-banana-beta",
"prompt": "A cat playing on the grass"
}
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({model: 'nano-banana-beta', prompt: 'A cat playing on the grass'})
};
fetch('https://api.evolink.ai/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/images/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'nano-banana-beta',
'prompt' => 'A cat playing on the grass'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/images/generations"
payload := strings.NewReader("{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/images/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/images/generations")
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 = "{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}"
response = http.request(request)
puts response.read_body{
"created": 1757165031,
"id": "task-unified-1757165031-uyujaw3d",
"model": "nano-banana-beta",
"object": "image.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 45
},
"type": "image",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 1.6,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: nano-banana-beta",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Nanobanana Image Generation Beta
- Le modèle Nano Banana (nano-banana-beta) prend en charge les modes texte-vers-image, image-vers-image, édition d’image et autres modes de génération
- Mode de traitement asynchrone, utilisez l’ID de tâche retourné pour interroger
- Les liens d’image générés sont valides pendant 24 heures, veuillez les enregistrer rapidement
curl --request POST \
--url https://api.evolink.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "nano-banana-beta",
"prompt": "A cat playing on the grass"
}
'import requests
url = "https://api.evolink.ai/v1/images/generations"
payload = {
"model": "nano-banana-beta",
"prompt": "A cat playing on the grass"
}
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({model: 'nano-banana-beta', prompt: 'A cat playing on the grass'})
};
fetch('https://api.evolink.ai/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/images/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'nano-banana-beta',
'prompt' => 'A cat playing on the grass'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/images/generations"
payload := strings.NewReader("{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/images/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/images/generations")
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 = "{\n \"model\": \"nano-banana-beta\",\n \"prompt\": \"A cat playing on the grass\"\n}"
response = http.request(request)
puts response.read_body{
"created": 1757165031,
"id": "task-unified-1757165031-uyujaw3d",
"model": "nano-banana-beta",
"object": "image.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 45
},
"type": "image",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 1.6,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: nano-banana-beta",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Autorisations
##Toutes les API nécessitent une authentification Bearer Token##
Obtenir une clé API :
Visitez la Page de gestion des clés API pour obtenir votre clé API
Ajouter à l'en-tête de requête :
Authorization: Bearer YOUR_API_KEY
Corps
Nom du modèle de génération d'image
Rétrocompatible : Le nom de modèle précédemment intégré gemini-2.5-flash-image reste utilisable et est automatiquement mappé vers nano-banana-beta
nano-banana-beta "nano-banana-beta"
Invite décrivant l'image à générer, ou décrivant comment éditer l'image d'entrée, limitée à 2000 tokens
2000"A cat playing in the grass"
Rapport d'aspect de l'image générée, valeur par défaut auto
auto, 1:1, 2:3, 3:2, 4:3, 3:4, 16:9, 9:16 Liste d'URL d'images de référence pour les fonctions image vers image et édition d'image
Remarque :
- Nombre maximum d'images d'entrée par requête :
5 - Taille d'image : ne dépassant pas
10MB - Formats de fichiers pris en charge :
.jpeg,.jpg,.png,.webp - Les URL d'images doivent être directement accessibles par le serveur, ou l'URL de l'image doit déclencher un téléchargement direct lors de l'accès (généralement ces URL se terminent par des extensions de fichiers image, telles que
.png,.jpg)
[ "https://example.com/image1.png", "https://example.com/image2.png" ]
Adresse de rappel HTTPS après l'achèvement de la tâche
Moment du rappel :
- Déclenché lorsque la tâche est terminée, échouée ou annulée
- Envoyé après confirmation de la facturation
Restrictions de sécurité :
- Seul le protocole HTTPS est pris en charge
- Les rappels vers les adresses IP internes sont interdits (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
- La longueur de l'URL ne doit pas dépasser
2048caractères
Mécanisme de rappel :
- Délai d'expiration :
10secondes - Maximum
3tentatives en cas d'échec (tentatives après1seconde/2secondes/4secondes) - Le format du corps de réponse du rappel est cohérent avec le format de réponse de l'API de requête de tâche
- Un code de statut 2xx renvoyé par l'adresse de rappel est considéré comme un succès, les autres codes de statut déclenchent une nouvelle tentative
"https://your-domain.com/webhooks/image-task-completed"
Réponse
Tâche de génération d'image créée avec succès
Horodatage de création de la tâche
1757165031
ID de tâche
"task-unified-1757165031-uyujaw3d"
Nom du modèle réellement utilisé
"nano-banana-beta"
Type de tâche spécifique
image.generation.task Pourcentage de progression de la tâche (0-100)
0 <= x <= 1000
Statut de la tâche
pending, processing, completed, failed "pending"
Informations sur la tâche asynchrone
Show child attributes
Show child attributes
Type de sortie de la tâche
text, image, audio, video "image"
Informations d'utilisation et de facturation
Show child attributes
Show child attributes