Picture editing

curl --request POST \
  --url https://api.tikway.ai/v1/images/edits \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.",
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png",
  "images": [
    {
      "image_url": "https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658"
    }
  ]
}
'

import requests

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

payload = {
    "model": "gpt-image-2",
    "prompt": "Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png",
    "images": [{ "image_url": "https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658" }]
}
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: 'Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.',
    size: '1024x1024',
    quality: 'high',
    output_format: 'png',
    images: [
      {
        image_url: 'https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658'
      }
    ]
  })
};

fetch('https://api.tikway.ai/v1/images/edits', 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/edits",
  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' => 'Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.',
    'size' => '1024x1024',
    'quality' => 'high',
    'output_format' => 'png',
    'images' => [
        [
                'image_url' => 'https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658'
        ]
    ]
  ]),
  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/edits"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\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/edits")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/v1/images/edits")

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\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\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
    }
  }
}

POST

https://api.tikway.ai

images

edits

Picture editing

curl --request POST \
  --url https://api.tikway.ai/v1/images/edits \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.",
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png",
  "images": [
    {
      "image_url": "https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658"
    }
  ]
}
'

import requests

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

payload = {
    "model": "gpt-image-2",
    "prompt": "Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png",
    "images": [{ "image_url": "https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658" }]
}
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: 'Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.',
    size: '1024x1024',
    quality: 'high',
    output_format: 'png',
    images: [
      {
        image_url: 'https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658'
      }
    ]
  })
};

fetch('https://api.tikway.ai/v1/images/edits', 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/edits",
  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' => 'Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.',
    'size' => '1024x1024',
    'quality' => 'high',
    'output_format' => 'png',
    'images' => [
        [
                'image_url' => 'https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658'
        ]
    ]
  ]),
  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/edits"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\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/edits")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/v1/images/edits")

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\": \"Keep the apple unchanged and replace only its background with a misty enchanted forest under soft cinematic lighting.\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"output_format\": \"png\",\n  \"images\": [\n    {\n      \"image_url\": \"https://gd-hbimg.huaban.com/cb36fdfc6ee4707de3ec666d6bc202fb99d9bef326a10d-oQHn3b_fw658\"\n    }\n  ]\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

images

object[]

required

Required. List of source images to be edited. The maximum number of GPT Image models is 16; each item must provide one of file_id or image_url. If uploading files directly, use the multipart field image[] (or images defined by your gateway).

Required array length: 1 - 16 elements

Hide child attributes

images.file_id

string

The ID of the source image file uploaded to the Files API.

images.image_url

string

Full image URL, or Base64 data URL.

prompt

string

required

Required. Text description of how you wish to edit or expand the image.

Minimum string length: 1

model

enum<string>

required

Required. Mockup for picture editing. dall-e-3 does not support image editing.

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,

chatgpt-image-latest,

dall-e-2

background

enum<string> | null

Output background, only supported by GPT Image model. When transparent, output_format must be png or webp.

Available options:

transparent,

opaque,

auto,

null

input_fidelity

enum<string> | null

The degree of consistency with the original input image, only supported GPT Image models apply.

Available options:

high,

low,

null

mask

object

Mask used for local redrawing. Choose one of file_id and image_url.

Hide child attributes

mask.file_id

string

File ID of the uploaded mask file.

mask.image_url

string

Mask image URL or Base64 data URL.

moderation

enum<string> | null

Content moderation level, only supported by the GPT Image model.

Available options:

low,

auto,

null

integer | null

The number of edited images to generate.

Required range: 1 <= x <= 10

output_compression

integer | null

Compression ratio (0–100) for jpeg or webp output, supported only by GPT Image model.

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 graphs generated in the streaming response.

Required range: 0 <= x <= 3

quality

enum<string> | null

Output quality. GPT Image supports low/medium/high/auto; GPT Image 2.5 additionally supports xhigh/max.

Available options:

low,

medium,

high,

xhigh,

max,

auto,

null

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,

1024x1024,

1536x1024,

1024x1536,

null

stream

boolean | null

Whether to return intermediate and final results as an SSE event stream.

user

string

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

response_format

enum<string>

default:b64_json

dall-e-2 is available as url or b64_json. GPT Image model fixedly returns Base64.

Available options:

b64_json,

url

Response

200 - application/json

created

integer

required

The Unix timestamp in seconds when the edit result was created.

data

object[]

required

Edited image list.

Hide child attributes

data.b64_json

string

Base64 encoded image content. The GPT Image model is returned by default.

data.revised_prompt

string

The actual revision prompt word of DALL·E 3; this editing interface usually does not return this field.

data.url

string

Generate image URL. DALL·E is provided when using the URL return format and is usually valid for 60 minutes.

background

enum<string>

The actual output context used.

Available options:

transparent,

opaque

output_format

enum<string>

Actual output format.

Available options:

png,

webp,

jpeg

quality

enum<string>

Output quality for actual use.

Available options:

low,

medium,

high,

auto

size

string

The actual generated image size.

usage

object

The token usage of the GPT Image model.

Hide child attributes

usage.input_tokens

integer

Enter the number of tokens for text and images.

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

Image generation

Video generation

Embeddings

Transcriptions

Picture editing

Authorizations

Body

Response