图片生成

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

图片生成

网关要求显式传入 model。不同模型只支持下表中的参数组合。

模型	尺寸	质量	模型专属参数
`gpt-image-2.5-sunburst` / `flare`（含快照）	任意 `WIDTHxHEIGHT`（16 倍数、1:3～3:1、最高 3840x2160）	`auto/low/medium/high/xhigh/max`	`background`、`moderation`、`output_format`、`output_compression`、`stream`、`partial_images`
`gpt-image-2`（含快照）	同上	`auto/low/medium/high`	同上；透明背景仍为预览能力
`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` 只能为 1；支持 `style`、`response_format`
`dall-e-2`	256×256、512×512、1024×1024	`standard`	支持 `n=1..10`、`response_format`

POST

https://api.tikway.ai

images

generations

图片生成

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
    }
  }
}

授权

Authorization

string

header

必填

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

请求体

application/json

prompt

string

必填

必填。要生成图像的文本描述；GPT Image 模型最长 32000 字符，dall-e-2 最长 1000 字符，dall-e-3 最长 4000 字符。

Required string length: 1 - 32000

model

enum<string>

必填

必填。图片生成模型。网关不会采用 OpenAI 的 dall-e-2 默认值，必须显式传 model。

可用选项:

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

背景设置，仅 GPT Image 模型支持。transparent 使用时 output_format 必须为 png 或 webp。

可用选项:

transparent,

opaque,

auto,

null

moderation

enum<string> | null

内容审核级别，仅 GPT Image 模型支持。auto 为默认值。

可用选项:

low,

auto,

null

integer | null

生成的图像数量。dall-e-3 仅支持 1。

必填范围: 1 <= x <= 10

output_compression

integer | null

图像压缩率（0–100），仅 GPT Image 的 webp 或 jpeg 输出支持，默认 100。

必填范围: 0 <= x <= 100

output_format

enum<string> | null

输出图像格式，仅 GPT Image 模型支持。

可用选项:

png,

jpeg,

webp,

null

partial_images

integer | null

流式响应中返回的中间图像数量，仅 GPT Image 模型支持。

必填范围: 0 <= x <= 3

quality

enum<string> | null

图像质量。GPT Image 支持 auto/low/medium/high；GPT Image 2.5 额外支持 xhigh/max；dall-e-3 支持 standard/hd；dall-e-2 仅支持 standard。

可用选项:

auto,

low,

medium,

high,

xhigh,

max,

standard,

hd,

null

response_format

enum<string>

默认值:b64_json

仅 dall-e-2 和 dall-e-3 支持 url 或 b64_json。GPT Image 模型始终返回 Base64，不支持此上游参数。

可用选项:

b64_json,

url

size

enum<string> | null

图像尺寸。GPT Image 2/2.5 支持 WIDTHxHEIGHT：宽高均为 16 的倍数、比例 1:3～3:1，最高 3840x2160；其他 GPT Image 使用 auto、1024x1024、1536x1024 或 1024x1536；dall-e-2 支持 256x256、512x512、1024x1024；dall-e-3 支持 1024x1024、1792x1024、1024x1792。

可用选项:

auto,

256x256,

512x512,

1024x1024,

1536x1024,

1024x1536,

1792x1024,

1024x1792,

null

stream

boolean | null

是否采用 SSE 流式生成，仅 GPT Image 模型支持，默认 false。

style

enum<string> | null

生成风格，仅 dall-e-3 支持。

可用选项:

vivid,

natural,

null

user

string

终端用户的唯一标识，用于滥用监控与检测。

响应

200 - application/json

created

integer

必填

图像创建时的 Unix 时间戳（秒）。

data

object[]

必填

生成结果列表。

Hide child attributes

data.b64_json

string

Base64 编码的图像数据。GPT Image 默认返回；DALL·E 在 response_format=b64_json 时返回。

data.revised_prompt

string

DALL·E 3 实际使用的修订提示词。

data.url

string<uri>

生成图像 URL。仅 DALL·E 且 response_format=url 时返回；有效期为 60 分钟。

background

enum<string>

实际采用的背景设置。

可用选项:

transparent,

opaque

output_format

enum<string>

实际输出图像格式。

可用选项:

png,

webp,

jpeg

quality

enum<string>

实际生成质量。

可用选项:

low,

medium,

high

size

string

实际生成的图像尺寸。

usage

object

GPT Image 模型的 token 用量。

Hide child attributes

usage.input_tokens

integer

输入（文本和图像）的 token 数。

usage.input_tokens_details

object

Hide child attributes

usage.input_tokens_details.image_tokens

integer

输入图像 token 数。

usage.input_tokens_details.text_tokens

integer

输入文本 token 数。

usage.output_tokens

integer

输出 token 数。

usage.output_tokens_details

object

Hide child attributes

usage.output_tokens_details.image_tokens

integer

输出图像 token 数。

usage.output_tokens_details.text_tokens

integer

输出文本 token 数。

usage.total_tokens

integer

输入和输出 token 总数。

对话补全

图片生成

视频生成

向量嵌入

语音转写

图片生成

授权

请求体

响应