Image generation

curl --request POST \
  --url https://api.tikway.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3-pro-image",
  "prompt": "Generate a photorealistic red apple on a rustic wooden table.",
  "size": "1:1",
  "quality": "standard"
}
'

import requests

url = "https://api.tikway.ai/v1/images/generations"

payload = {
    "model": "gemini-3-pro-image",
    "prompt": "Generate a photorealistic red apple on a rustic wooden table.",
    "size": "1:1",
    "quality": "standard"
}
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: 'gemini-3-pro-image',
    prompt: 'Generate a photorealistic red apple on a rustic wooden table.',
    size: '1:1',
    quality: 'standard'
  })
};

fetch('https://api.tikway.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.tikway.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' => 'gemini-3-pro-image',
    'prompt' => 'Generate a photorealistic red apple on a rustic wooden table.',
    'size' => '1:1',
    'quality' => 'standard'
  ]),
  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.tikway.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\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.tikway.ai/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.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\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\n}"

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

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "usage": {
    "total_tokens": 100,
    "input_tokens": 50,
    "output_tokens": 50,
    "input_tokens_details": {
      "text_tokens": 10,
      "image_tokens": 40
    }
  }
}

Nano Banana

Image generation

Unified OpenAI compatible portal. size represents the aspect ratio, and quality maps to Gemini’s image resolution.

Model	Output resolution	Reference image	Search and thinking
`gemini-3.1-flash-image`	512px, 1K, 2K, 4K; supports 1:4/4:1/1:8/8:1 extreme ratios	Up to 14 images (max 10 objects + 4 characters)	`google_search`, `image_search`, `thinking_level`
`gemini-3-pro-image`	1K, 2K, 4K	Up to 14 images (up to 6 objects + 5 characters + 3 styles)	`google_search`, `thinking_level`; image search is not supported
`gemini-2.5-flash-image`	Fixed 1K	Recommended maximum 3 images	Does not support Google Search, image search and thinking

This entry does not accept native generationConfig, aspect_ratio or image_size, please use size and quality.

POST

https://api.tikway.ai

images

generations

Image generation

curl --request POST \
  --url https://api.tikway.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3-pro-image",
  "prompt": "Generate a photorealistic red apple on a rustic wooden table.",
  "size": "1:1",
  "quality": "standard"
}
'

import requests

url = "https://api.tikway.ai/v1/images/generations"

payload = {
    "model": "gemini-3-pro-image",
    "prompt": "Generate a photorealistic red apple on a rustic wooden table.",
    "size": "1:1",
    "quality": "standard"
}
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: 'gemini-3-pro-image',
    prompt: 'Generate a photorealistic red apple on a rustic wooden table.',
    size: '1:1',
    quality: 'standard'
  })
};

fetch('https://api.tikway.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.tikway.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' => 'gemini-3-pro-image',
    'prompt' => 'Generate a photorealistic red apple on a rustic wooden table.',
    'size' => '1:1',
    'quality' => 'standard'
  ]),
  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.tikway.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\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.tikway.ai/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.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\": \"gemini-3-pro-image\",\n  \"prompt\": \"Generate a photorealistic red apple on a rustic wooden table.\",\n  \"size\": \"1:1\",\n  \"quality\": \"standard\"\n}"

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

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "usage": {
    "total_tokens": 100,
    "input_tokens": 50,
    "output_tokens": 50,
    "input_tokens_details": {
      "text_tokens": 10,
      "image_tokens": 40
    }
  }
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model

enum<string>

required

Required. Gemini picture model. See the interface description for the resolution, search, thinking and reference map limitations of different models.

Available options:

gemini-3.1-flash-image,

gemini-3-pro-image,

gemini-2.5-flash-image

Minimum string length: 1

prompt

string

required

Required. Generate prompt words for pictures.

Required string length: 1 - 32000

images

(string | object)[]

Optional. Reference image array; at least 1 image is used for image editing. URL/data URL string or object containing image_url can be passed; file_id is not supported. See the interface description for the upper limit of the model.

Required array length: 1 - 14 elements

size

enum<string>

Output aspect ratio. The gateway reduces and maps this field to Gemini aspectRatio; it is not a pixel dimension. Extreme ratios 1:4, 4:1, 1:8, 8:1 are only supported by gemini-3.1-flash-image.

Available options:

1:1,

1:4,

1:8,

2:3,

3:2,

3:4,

4:1,

4:3,

4:5,

5:4,

8:1,

9:16,

16:9,

21:9

quality

enum<string>

Output resolution mapping: low→512px, standard→1K, medium→2K, high/hd→4K, auto/omitted→not specified. gemini-2.5-flash-image only supports 1K.

Available options:

standard,

hd,

low,

medium,

high,

auto

google_search

boolean

Gemini native extension, whether to enable Google Search grounding; only available for models that support this capability.

image_search

boolean

Gemini native extension, whether to enable image search grounding; only available for models that support this capability.

thinking_level

enum<string>

Gemini native extension, model thinking intensity; only models that support this capability are available.

Available options:

Minimal,

High

response_format

enum<string>

default:b64_json

Fixed returning Base64 image so that the response conforms to the Response Schema of this interface.

Available options:

b64_json,

url

Response

200 - application/json

created

integer

required

Unix timestamp in seconds when the image was created.

data

object[]

required

Generate a list of results.

Hide child attributes

data.b64_json

string

Base64 encoded image data. GPT Image is returned by default; DALL·E is returned when response_format=b64_json.

data.revised_prompt

string

DALL·E 3 Revision prompt words actually used.

data.url

string<uri>

Generate image URL. Returned only when DALL·E and response_format=url; valid for 60 minutes.

background

enum<string>

The actual background settings used.

Available options:

transparent,

opaque

output_format

enum<string>

Actual output image format.

Available options:

png,

webp,

jpeg

quality

enum<string>

Actual build quality.

Available options:

low,

medium,

high

size

string

The actual resulting image size.

usage

object

The token usage of the GPT Image model.

Hide child attributes

usage.input_tokens

integer

Number of tokens for input (text and image).

usage.input_tokens_details

object

Hide child attributes

usage.input_tokens_details.image_tokens

integer

Enter the number of image tokens.

usage.input_tokens_details.text_tokens

integer

Enter the text token number.

usage.output_tokens

integer

Output the number of tokens.

usage.output_tokens_details

object

Hide child attributes

usage.output_tokens_details.image_tokens

integer

Output the number of image tokens.

usage.output_tokens_details.text_tokens

integer

Output text token number.

usage.total_tokens

integer

The total number of input and output tokens.

Chat completions