Nano Banana
curl --request POST \
--url https://api.krea.ai/generate/image/google/nano-banana \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "An ornate palace surrounded by moats and lush manicured gardens."
}
'import requests
url = "https://api.krea.ai/generate/image/google/nano-banana"
payload = { "prompt": "An ornate palace surrounded by moats and lush manicured gardens." }
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({prompt: 'An ornate palace surrounded by moats and lush manicured gardens.'})
};
fetch('https://api.krea.ai/generate/image/google/nano-banana', 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.krea.ai/generate/image/google/nano-banana",
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([
'prompt' => 'An ornate palace surrounded by moats and lush manicured gardens.'
]),
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.krea.ai/generate/image/google/nano-banana"
payload := strings.NewReader("{\n \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\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.krea.ai/generate/image/google/nano-banana")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.krea.ai/generate/image/google/nano-banana")
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 \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\n}"
response = http.request(request)
puts response.read_body{
"job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "backlogged",
"created_at": "2023-11-07T05:31:56Z",
"completed_at": null,
"result": null,
"error": {
"code": "<string>",
"message": "<string>"
}
}{
"error": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}Image
Nano Banana
Most versatile intelligent model.
POST
/
generate
/
image
/
google
/
nano-banana
Nano Banana
curl --request POST \
--url https://api.krea.ai/generate/image/google/nano-banana \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "An ornate palace surrounded by moats and lush manicured gardens."
}
'import requests
url = "https://api.krea.ai/generate/image/google/nano-banana"
payload = { "prompt": "An ornate palace surrounded by moats and lush manicured gardens." }
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({prompt: 'An ornate palace surrounded by moats and lush manicured gardens.'})
};
fetch('https://api.krea.ai/generate/image/google/nano-banana', 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.krea.ai/generate/image/google/nano-banana",
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([
'prompt' => 'An ornate palace surrounded by moats and lush manicured gardens.'
]),
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.krea.ai/generate/image/google/nano-banana"
payload := strings.NewReader("{\n \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\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.krea.ai/generate/image/google/nano-banana")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.krea.ai/generate/image/google/nano-banana")
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 \"prompt\": \"An ornate palace surrounded by moats and lush manicured gardens.\"\n}"
response = http.request(request)
puts response.read_body{
"job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "backlogged",
"created_at": "2023-11-07T05:31:56Z",
"completed_at": null,
"result": null,
"error": {
"code": "<string>",
"message": "<string>"
}
}{
"error": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}Pricing
Fixed API prices in USD.
Deprecated request aliases
Deprecated request aliases
These aliases are accepted for compatibility only and are not shown in the request schema.
| Deprecated | Use instead | Accepted until |
|---|---|---|
imageUrls | image_urls | 2026-06-19 |
aspectRatio | aspect_ratio | 2026-06-19 |
style_images | image_urls | 2026-09-11 |
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
URL to receive a POST request when the job completes. The webhook will receive the job data including results.
Body
application/json
Minimum string length:
1Width of the generated image.
Height of the generated image.
Image prompts to use for the generation.
Can be an external URL, base64 data URI, or uploaded asset URL.
Maximum string length:
1024Available options:
21:9, 1:1, 4:3, 3:2, 2:3, 5:4, 4:5, 3:4, 16:9, 9:16 Response
The resulting job data. This will be returned in a pending state until the job is completed. See /jobs/{id} for retrieving the results.
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Available options:
backlogged, queued, scheduled, processing, sampling, intermediate-complete, completed, failed, cancelled Pattern:
^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$Show child attributes
Show child attributes
Was this page helpful?