Images API

The Images API provides AI image generation capabilities, supporting image creation from text descriptions, image editing, and generating image variations.

Basic Information

API Endpoints

Image generation: https://api.routin.ai/v1/images/generations
Image editing: https://api.routin.ai/v1/images/edits
Image variations: https://api.routin.ai/v1/images/variations

Authentication Add your API Key in the request header:

Authorization: Bearer YOUR_API_KEY

MeteorAI is fully compatible with the OpenAI Images API, supporting DALL·E 3, DALL·E 2, and other image generation models.

1. Image Generation

Generate brand new images from text descriptions.

Request Parameters

Parameter	Type	Required	Description
`prompt`	string	Yes	Image description, up to 4000 characters
`model`	string	No	Model name, such as `dall-e-3`, `dall-e-2`
`n`	integer	No	Number of images to generate (1-10), DALL·E 3 only supports 1
`size`	string	No	Image size, such as `1024x1024`, `1792x1024`, `1024x1792`
`quality`	string	No	Image quality: `standard` or `hd` (DALL·E 3 only)
`style`	string	No	Style: `vivid` or `natural` (DALL·E 3 only)
`response_format`	string	No	Return format: `url` or `b64_json`

Response Format

{
  "created": 1677652288,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "Optimized prompt"
    }
  ]
}

Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.routin.ai/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="一只可爱的橙色小猫在草地上玩耍,水彩画风格",
    size="1024x1024",
    quality="standard",
    n=1
)

image_url = response.data[0].url
print(f"Image URL: {image_url}")
print(f"Revised prompt: {response.data[0].revised_prompt}")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

async function main() {
  const response = await client.images.generate({
    model: 'dall-e-3',
    prompt: '一只可爱的橙色小猫在草地上玩耍,水彩画风格',
    size: '1024x1024',
    quality: 'standard',
    n: 1,
  });

  const imageUrl = response.data[0].url;
  console.log(`Image URL: ${imageUrl}`);
  console.log(`Revised prompt: ${response.data[0].revised_prompt}`);
}

main();

const OpenAI = require('openai');

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

client.images.generate({
  model: 'dall-e-3',
  prompt: '一只可爱的橙色小猫在草地上玩耍,水彩画风格',
  size: '1024x1024',
  quality: 'standard',
  n: 1,
}).then(response => {
  const imageUrl = response.data[0].url;
  console.log(`Image URL: ${imageUrl}`);
  console.log(`Revised prompt: ${response.data[0].revised_prompt}`);
});

using OpenAI.Images;

var client = new ImageClient(
    model: "dall-e-3",
    apiKey: "YOUR_API_KEY",
    new OpenAIClientOptions
    {
        Endpoint = new Uri("https://api.routin.ai/v1")
    }
);

var response = await client.GenerateImageAsync(
    "一只可爱的橙色小猫在草地上玩耍,水彩画风格",
    new ImageGenerationOptions
    {
        Size = GeneratedImageSize.W1024xH1024,
        Quality = GeneratedImageQuality.Standard,
        ResponseFormat = GeneratedImageFormat.Uri
    }
);

var imageUrl = response.Value.ImageUri;
Console.WriteLine($"Image URL: {imageUrl}");
Console.WriteLine($"Revised prompt: {response.Value.RevisedPrompt}");

curl https://api.routin.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "一只可爱的橙色小猫在草地上玩耍,水彩画风格",
    "size": "1024x1024",
    "quality": "standard",
    "n": 1
  }'

Download and Save Image

from openai import OpenAI
import requests
from pathlib import Path

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.routin.ai/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="未来城市的夜景,赛博朋克风格",
    size="1024x1024"
)

# Download image
image_url = response.data[0].url
image_data = requests.get(image_url).content

# Save locally
output_path = Path("generated_image.png")
output_path.write_bytes(image_data)
print(f"Image saved to: {output_path}")

import OpenAI from 'openai';
import fs from 'fs';
import https from 'https';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

async function main() {
  const response = await client.images.generate({
    model: 'dall-e-3',
    prompt: '未来城市的夜景,赛博朋克风格',
    size: '1024x1024',
  });

  const imageUrl = response.data[0].url!;
  const file = fs.createWriteStream('generated_image.png');

  https.get(imageUrl, (response) => {
    response.pipe(file);
    file.on('finish', () => {
      file.close();
      console.log('Image saved to: generated_image.png');
    });
  });
}

main();

using OpenAI.Images;

var client = new ImageClient(
    model: "dall-e-3",
    apiKey: "YOUR_API_KEY",
    new OpenAIClientOptions
    {
        Endpoint = new Uri("https://api.routin.ai/v1")
    }
);

var response = await client.GenerateImageAsync(
    "未来城市的夜景,赛博朋克风格",
    new ImageGenerationOptions
    {
        Size = GeneratedImageSize.W1024xH1024
    }
);

// Download image
using var httpClient = new HttpClient();
var imageBytes = await httpClient.GetByteArrayAsync(response.Value.ImageUri);

// Save locally
await File.WriteAllBytesAsync("generated_image.png", imageBytes);
Console.WriteLine("Image saved to: generated_image.png");

2. Image Editing

Edit specified areas of existing images based on prompts.

Request Parameters

Parameter	Type	Required	Description
`image`	file	Yes	Image file to edit (PNG, < 4MB)
`mask`	file	No	Transparent areas indicate parts to edit
`prompt`	string	Yes	Edit description
`model`	string	No	Model name, default `dall-e-2`
`n`	integer	No	Number of images to generate (1-10)
`size`	string	No	Image size

Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.routin.ai/v1"
)

response = client.images.edit(
    model="dall-e-2",
    image=open("original.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="在透明区域添加一只蝴蝶",
    n=1,
    size="1024x1024"
)

image_url = response.data[0].url
print(f"Edited image: {image_url}")

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

async function main() {
  const response = await client.images.edit({
    model: 'dall-e-2',
    image: fs.createReadStream('original.png'),
    mask: fs.createReadStream('mask.png'),
    prompt: '在透明区域添加一只蝴蝶',
    n: 1,
    size: '1024x1024',
  });

  const imageUrl = response.data[0].url;
  console.log(`Edited image: ${imageUrl}`);
}

main();

using OpenAI.Images;

var client = new ImageClient(
    model: "dall-e-2",
    apiKey: "YOUR_API_KEY",
    new OpenAIClientOptions
    {
        Endpoint = new Uri("https://api.routin.ai/v1")
    }
);

using var imageStream = File.OpenRead("original.png");
using var maskStream = File.OpenRead("mask.png");

var response = await client.GenerateImageEditAsync(
    imageStream,
    "在透明区域添加一只蝴蝶",
    new ImageEditOptions
    {
        Mask = maskStream,
        Size = GeneratedImageSize.W1024xH1024
    }
);

var imageUrl = response.Value.ImageUri;
Console.WriteLine($"Edited image: {imageUrl}");

curl https://api.routin.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F image="@original.png" \
  -F mask="@mask.png" \
  -F prompt="在透明区域添加一只蝴蝶" \
  -F model="dall-e-2" \
  -F n=1 \
  -F size="1024x1024"

3. Image Variations

Generate similar variations of the original image.

Request Parameters

Parameter	Type	Required	Description
`image`	file	Yes	Source image file (PNG, < 4MB)
`model`	string	No	Model name, default `dall-e-2`
`n`	integer	No	Number of images to generate (1-10)
`size`	string	No	Image size

Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.routin.ai/v1"
)

response = client.images.create_variation(
    model="dall-e-2",
    image=open("original.png", "rb"),
    n=2,
    size="1024x1024"
)

for i, image_data in enumerate(response.data):
    print(f"Variation {i+1}: {image_data.url}")

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

async function main() {
  const response = await client.images.createVariation({
    model: 'dall-e-2',
    image: fs.createReadStream('original.png'),
    n: 2,
    size: '1024x1024',
  });

  response.data.forEach((imageData, i) => {
    console.log(`Variation ${i + 1}: ${imageData.url}`);
  });
}

main();

using OpenAI.Images;

var client = new ImageClient(
    model: "dall-e-2",
    apiKey: "YOUR_API_KEY",
    new OpenAIClientOptions
    {
        Endpoint = new Uri("https://api.routin.ai/v1")
    }
);

using var imageStream = File.OpenRead("original.png");

var response = await client.GenerateImageVariationsAsync(
    imageStream,
    2,
    new ImageVariationOptions
    {
        Size = GeneratedImageSize.W1024xH1024
    }
);

for (int i = 0; i < response.Value.Count; i++)
{
    Console.WriteLine($"Variation {i + 1}: {response.Value[i].ImageUri}");
}

curl https://api.routin.ai/v1/images/variations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F image="@original.png" \
  -F model="dall-e-2" \
  -F n=2 \
  -F size="1024x1024"

Supported Models

DALL·E 3

Sizes: 1024x1024, 1792x1024, 1024x1792
Quality: standard, hd
Style: vivid, natural
Features: Higher image quality and detail, supports prompt optimization

DALL·E 2

Sizes: 256x256, 512x512, 1024x1024
Features: Supports image editing and variation generation, lower cost

DALL·E 3 only supports generating single images, while DALL·E 2 supports batch generation and image editing features.

Best Practices

1. Write Effective Prompts

# ❌ Poor prompt
prompt = "一只猫"

# ✅ Good prompt
prompt = "一只毛茸茸的橙色波斯猫,坐在天鹅绒沙发上,柔和的自然光线,专业摄影,浅景深"

Prompt Elements:

Subject: Describe the main object to generate
Details: Color, texture, style
Environment: Background, scene, lighting
Art style: Oil painting, watercolor, 3D rendering, etc.
Perspective: Front view, side view, bird's eye view, etc.

2. Use Negative Prompts (by describing what to avoid)

# Specify unwanted elements in the prompt
prompt = "一个现代化的厨房,干净整洁,没有杂物,没有人物"

# Generate initial version
response1 = client.images.generate(
    model="dall-e-3",
    prompt="一座未来城市"
)

# Refine prompt based on results
response2 = client.images.generate(
    model="dall-e-3",
    prompt="一座未来城市,高耸的摩天大楼,霓虹灯,夜景,雨后湿润的街道,赛博朋克风格"
)

4. Cost Optimization

# Use standard quality for development/testing
response = client.images.generate(
    model="dall-e-3",
    prompt=prompt,
    quality="standard"  # Lower cost
)

# Use hd for production when high quality is needed
response = client.images.generate(
    model="dall-e-3",
    prompt=prompt,
    quality="hd"  # Higher quality, higher cost
)

5. Base64 Format for Immediate Display

# Use base64 format to avoid additional network requests
response = client.images.generate(
    model="dall-e-3",
    prompt=prompt,
    response_format="b64_json"
)

import base64
image_data = base64.b64decode(response.data[0].b64_json)
# Use image data directly in application

Use Cases

Content Creation: Generate images for blogs and social media
Product Design: Quickly generate product prototypes and concept art
Marketing Materials: Create ads, posters, banners
Game Development: Generate game assets and concept art
Education: Create teaching illustrations and diagrams
E-commerce: Generate product scenes and usage scenarios

Error Handling

Image generation may be rejected due to content policy violations. Ensure prompts comply with usage guidelines.

from openai import OpenAI, APIError

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.routin.ai/v1"
)

try:
    response = client.images.generate(
        model="dall-e-3",
        prompt="测试提示词"
    )
    print(response.data[0].url)
except APIError as e:
    if "content_policy_violation" in str(e):
        print("Prompt violates content policy, please modify and retry")
    else:
        print(f"API error: {e}")
except Exception as e:
    print(f"Unknown error: {e}")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.routin.ai/v1',
});

async function main() {
  try {
    const response = await client.images.generate({
      model: 'dall-e-3',
      prompt: '测试提示词',
    });
    console.log(response.data[0].url);
  } catch (error: any) {
    if (error.code === 'content_policy_violation') {
      console.error('Prompt violates content policy, please modify and retry');
    } else {
      console.error(`Error: ${error.message}`);
    }
  }
}

main();

using OpenAI.Images;
using OpenAI;

var client = new ImageClient(
    model: "dall-e-3",
    apiKey: "YOUR_API_KEY",
    new OpenAIClientOptions
    {
        Endpoint = new Uri("https://api.routin.ai/v1")
    }
);

try
{
    var response = await client.GenerateImageAsync("测试提示词");
    Console.WriteLine(response.Value.ImageUri);
}
catch (ClientResultException ex) when (ex.Message.Contains("content_policy"))
{
    Console.WriteLine("Prompt violates content policy, please modify and retry");
}
catch (Exception ex)
{
    Console.WriteLine($"Error: {ex.Message}");
}

Common Error Codes

Error Code	Description	Solution
401	Invalid API Key	Check Authorization header
400	Invalid request parameters	Check image format, size, and parameters
400	Content policy violation	Modify prompt to ensure compliance
429	Rate limit exceeded	Reduce request frequency
500	Server error	Retry later

Content Policy

Ensure generated image content complies with the following guidelines:

No violent, pornographic, hateful, or illegal content
No infringement of others' copyright, portrait rights, or other rights
No misleading or false information
Comply with local laws and regulations

Requests violating content policy will be rejected. Frequent violations may result in API Key suspension.

More Resources

Chat Completions API - Chat interface
Embeddings API - Text embeddings interface
Audio API - Speech recognition and synthesis interface

Images API

Images API

Basic Information

1. Image Generation

Request Parameters

Response Format

Code Examples

Download and Save Image

2. Image Editing

Request Parameters

Code Examples

3. Image Variations

Request Parameters

Code Examples

Supported Models

DALL·E 3

DALL·E 2

Best Practices

1. Write Effective Prompts

2. Use Negative Prompts (by describing what to avoid)

3. Iterative Refinement

4. Cost Optimization

5. Base64 Format for Immediate Display

Use Cases

Error Handling

Common Error Codes

Content Policy

More Resources

On this page