Image generation

curl --request POST \
  --url https://api.tikway.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.",
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png"
}
'

import requests

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

payload = {
    "model": "gpt-image-2",
    "prompt": "Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png"
}
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: 'gpt-image-2',
    prompt: 'Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.',
    size: '1024x1024',
    quality: 'high',
    output_format: 'png'
  })
};

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' => 'gpt-image-2',
    'prompt' => 'Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.',
    'size' => '1024x1024',
    'quality' => 'high',
    'output_format' => 'png'
  ]),
  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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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
    }
  }
}

GPT Image

Image generation

The gateway requires model to be passed in explicitly. Different models only support parameter combinations in the table below.

Model	Dimensions	Quality	Model-specific parameters
`gpt-image-2.5-sunburst` / `flare` (including snapshots)	Any `WIDTHxHEIGHT` (16 multiples, 1:3~3:1, up to 3840x2160)	`auto/low/medium/high/xhigh/max`	`background`, `moderation`, `output_format`, `output_compression`, `stream`, `partial_images`
`gpt-image-2` (including snapshots)	Same as above	`auto/low/medium/high`	Same as above; transparent background is still a preview capability
`gpt-image-1` / `1.5` / `1-mini`	`auto`, 1024×1024, 1536×1024, 1024×1536	`auto/low/medium/high`	`background`, `moderation`, `output_format`, `output_compression`, `stream`, `partial_images`
`dall-e-3`	1024×1024, 1792×1024, 1024×1792	`standard/hd`	`n` can only be 1; supports `style`, `response_format`
`dall-e-2`	256×256, 512×512, 1024×1024	`standard`	Support `n=1..10`, `response_format`

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": "gpt-image-2",
  "prompt": "Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.",
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png"
}
'

import requests

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

payload = {
    "model": "gpt-image-2",
    "prompt": "Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png"
}
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: 'gpt-image-2',
    prompt: 'Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.',
    size: '1024x1024',
    quality: 'high',
    output_format: 'png'
  })
};

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' => 'gpt-image-2',
    'prompt' => 'Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.',
    'size' => '1024x1024',
    'quality' => 'high',
    'output_format' => 'png'
  ]),
  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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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\": \"gpt-image-2\",\n  \"prompt\": \"Generate a photorealistic red apple resting on a rustic wooden table, soft window light, shallow depth of field.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\"\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

prompt

string

required

Required. To generate a text description of the image; GPT Image model has a maximum length of 32,000 characters, dall-e-2 has a maximum length of 1,000 characters, and dall-e-3 has a maximum length of 4,000 characters.

Required string length: 1 - 32000

model

enum<string>

required

Required. Image generation model. The gateway will not adopt OpenAI's dall-e-2 default value, and the model must be passed explicitly.

Available options:

gpt-image-2.5-sunburst,

gpt-image-2.5-sunburst-2026-09-08,

gpt-image-2.5-flare,

gpt-image-2.5-flare-2026-09-08,

gpt-image-2,

gpt-image-2-2026-04-21,

gpt-image-1.5,

gpt-image-1,

gpt-image-1-mini,

dall-e-2,

dall-e-3

background

enum<string> | null

Background settings, only supported by GPT Image model. When using transparent output_format must be png or webp.

Available options:

transparent,

opaque,

auto,

null

moderation

enum<string> | null

Content moderation level, only supported by the GPT Image model. auto is the default value.

Available options:

low,

auto,

null

integer | null

The number of images generated. dall-e-3 only supports 1.

Required range: 1 <= x <= 10

output_compression

integer | null

Image compression ratio (0–100), only supported by webp or jpeg output of GPT Image, default 100.

Required range: 0 <= x <= 100

output_format

enum<string> | null

Output image format, only supported by GPT Image model.

Available options:

png,

jpeg,

webp,

null

partial_images

integer | null

The number of intermediate images returned in the streaming response, only supported by the GPT Image model.

Required range: 0 <= x <= 3

quality

enum<string> | null

Image quality. GPT Image supports auto/low/medium/high; GPT Image 2.5 additionally supports xhigh/max; dall-e-3 supports standard/hd; dall-e-2 only supports standard.

Available options:

auto,

low,

medium,

high,

xhigh,

max,

standard,

hd,

null

response_format

enum<string>

default:b64_json

Only dall-e-2 and dall-e-3 support url or b64_json. The GPT Image model always returns Base64 and this upstream parameter is not supported.

Available options:

b64_json,

url

size

enum<string> | null

Image size. GPT Image 2/2.5 supports WIDTHxHEIGHT: width and height are multiples of 16, ratio 1:3~3:1, up to 3840x2160; other GPT Images use auto, 1024x1024, 1536x1024 or 1024x1536; supported by dall-e-2 256x256, 512x512, 1024x1024; dall-e-3 supports 1024x1024, 1792x1024, 1024x1792.

Available options:

auto,

256x256,

512x512,

1024x1024,

1536x1024,

1024x1536,

1792x1024,

1024x1792,

null

stream

boolean | null

Whether to use SSE streaming generation, only supported by GPT Image model, default false.

style

enum<string> | null

Generate style, only supported by dall-e-3.

Available options:

vivid,

natural,

null

user

string

The unique identifier of the end user, used for abuse monitoring and detection.

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