Image Generation - MixRoute API

curl --request POST \
  --url https://api.mixroute.ai/v1/images/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "seedream-4.0-base",
    "prompt": "A cute orange kitten sitting in a garden",
    "size": "1024x1024",
    "n": 1
  }'

{
  "created": 1709459123,
  "data": [
    {
      "url": "https://example.com/generated-image.png",
      "revised_prompt": "A cute orange kitten sitting in a garden"
    }
  ]
}

POST

images

generations

curl --request POST \
  --url https://api.mixroute.ai/v1/images/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "seedream-4.0-base",
    "prompt": "A cute orange kitten sitting in a garden",
    "size": "1024x1024",
    "n": 1
  }'

{
  "created": 1709459123,
  "data": [
    {
      "url": "https://example.com/generated-image.png",
      "revised_prompt": "A cute orange kitten sitting in a garden"
    }
  ]
}

Introduction

The image generation API supports text-to-image, image-to-image, image editing, and more. Through a unified API interface, you can call multiple mainstream image generation models including Gemini, Doubao Seedream, GPT Image, and Qwen.

Authentication

Bearer Token, e.g., Bearer sk-xxxxxxxxxx

Request Parameters

model

string

required

Model identifier, supported models include:

Qwen series: qwen-image-plus, qwen-image-edit-plus, etc.
GPT Image series: gpt-image-1, etc.
Doubao Seedream series: doubao-seedream-3-0-t2i-250415, doubao-seedream-4-0-250828, doubao-seedream-4-5-251128, doubao-seededit-3-0-i2i-250628, etc.
Gemini series: gemini-2.5-flash-image (Nano Banana), gemini-3-pro-image-preview (Nano Banana Pro), etc.

prompt

string

Text-to-image prompt

response_format

string

Response format: b64_json or urlNote: Different models have different support for response_format:

Qwen series: Supports both b64_json and url
GPT Image series: Only supports b64_json format
Doubao Seedream series: Usually returns URL links
Gemini series: Only supports b64_json format

contents

array

Multi-turn content for image-to-image or context conversations

Basic Examples

Gemini
Doubao Seedream
GPT Image
Qwen

Text-to-Image
Image-to-Image

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "gemini-2.5-flash-image",
  "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
  "size": "16:9",
  "quality": "high",
  "n": 1,
  "temperature":1.1,
  "top_p":0.95,
  "response_format": "b64_json",
  "image_size": "2K",
  "mime_type": "image/png",
  "response_modalities": "image"
}'

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "gemini-2.5-flash-image",
  "size": "16:9",
  "quality": "high",
  "image_size": "3K",
  "temperature":1.1,
  "top_p":0.95,
  "response_format": "b64_json",
  "contents": [
    {
      "role": "user",
      "parts": [
        {"text": "Generate an aerial view of Canton Tower based on this image"},
        {"image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."}
      ]
    }
  ]
}'

Text-to-Image
Image-to-Image

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "doubao-seedream-4-0-250828",
  "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
  "size": "2048x2048",
  "watermark": false,
  "seed": 12345,
  "optimize_prompt_options": {
    "mode": "standard"
  }
}'

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "doubao-seedream-4-0-250828",
  "prompt": "Transform this image into oil painting style",
  "size": "2048x2048",
  "watermark": false,
  "seed": 12345,
  "contents": [
    {
      "role": "user",
      "parts": [
        {"image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."},
        {"text": "Transform this image into oil painting style"}
      ]
    }
  ]
}'

Text-to-Image
Image-to-Image

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "gpt-image-1",
  "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
  "size": "1024x1024",
  "quality": "high",
  "n": 1
}'

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "gpt-image-1",
  "prompt": "Transform this image into oil painting style",
  "size": "1024x1024",
  "quality": "high",
  "input_fidelity": "medium",
  "n": 1,
  "image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."
}'

Text-to-Image

curl -X POST "https://api.mixroute.ai/v1/images/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen-image-plus",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "An elegant couplet hanging in a traditional Chinese hall"
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "1",
    "prompt_extend": true,
    "seed": "4",
    "watermark": true
  }
}'

{
  "code": 200,
  "msg": "Success",
  "data": {
    "data": [
      {
        "url": "",
        "b64_json": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQA...",
        "revised_prompt": ""
      }
    ],
    "created": 1757320007
  }
}

Model-Specific Parameters

Doubao Seedream

size

string

Image size, depends on model version:

doubao-seedream-4.0/4.5: 2048x2048, 2304x1728, etc. (2K/4K)
doubao-seedream-3.0: 1024x1024, 1152x864, etc.

watermark

boolean

Whether to add watermark

seed

integer

Random seed for controlling generation randomness. Range: 0 to 2147483647

guidance_scale

number

Guidance coefficient. Recommended range: 1.0-10.0, default: 2.5

sequential_image_generation

string

Sequential image generation switch: "disabled" (default) or "auto"

GPT Image

size

string

Image size: 1024x1024, 1024x1536, 1536x1024. Default: 1024x1024

quality

string

Image quality: "high", "medium", "low"

integer

Number of images to generate. Range: 1-10

input_fidelity

string

Input fidelity for image-to-image: "auto", "high", "medium", "low"

Gemini

size

string

Aspect ratio: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

image_size

string

Image size: 1K (default), 2K, 4K

mime_type

string

Output format: image/png (default), image/jpeg

Supported Models

Gemini Series

Model Name	Core Capabilities
`gemini-2.5-flash-image` (Nano Banana)	Text-to-image, image-to-image, multi-image fusion
`gemini-3-pro-image-preview` (Nano Banana Pro)	Higher quality output, text-to-image, image-to-image

Doubao Seedream Series

Model Name	Core Capabilities
`doubao-seedream-3-0-t2i-250415`	Text-to-image, seed control, guidance coefficient
`doubao-seedream-4-0-250828`	Text-to-image, image-to-image, multi-image fusion, 2K/4K
`doubao-seedream-4-5-251128`	Text-to-image, image-to-image, prompt optimization
`doubao-seededit-3-0-i2i-250628`	Image editing, style transfer

GPT Image Series

Model Name	Core Capabilities
`gpt-image-1`	Text-to-image, image-to-image, multi-image fusion
`gpt-image-1-mini`	Lower cost, faster speed

Qwen Series

Model Name	Core Capabilities
`qwen-image-plus`	Text-to-image, text rendering, prompt extension
`qwen-image-edit-plus`	Image editing, style transfer

FAQ

What image formats are supported?

Different models support different formats:

Qwen: JPEG, JPG, PNG, BMP, TIFF, WEBP, max 10MB
GPT Image: JPEG, PNG, GIF, WEBP, max 10MB
Doubao Seedream 4.x: JPEG, PNG, WEBP, BMP, TIFF, GIF, max 10MB
Gemini: PNG, JPEG, JPG, WEBP, max 7MB

How long are generated images valid?

Image URLs are valid for approximately 24 hours. It is recommended to download and save immediately after receiving the response.

Can I generate multiple images at once?

GPT Image: Use n parameter (1-10 images)
Doubao Seedream 4.x: Use sequential image generation (1-4 images)
Qwen: 1 image per request, make multiple concurrent requests for more

curl --request POST \
  --url https://api.mixroute.ai/v1/images/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "seedream-4.0-base",
    "prompt": "A cute orange kitten sitting in a garden",
    "size": "1024x1024",
    "n": 1
  }'

{
  "created": 1709459123,
  "data": [
    {
      "url": "https://example.com/generated-image.png",
      "revised_prompt": "A cute orange kitten sitting in a garden"
    }
  ]
}

Gemini Native (Image)Gemini Native (Video)

​Introduction

​Authentication

​Request Parameters

​Basic Examples

​Model-Specific Parameters

​Doubao Seedream

​GPT Image

​Gemini

​Supported Models

​Gemini Series

​Doubao Seedream Series

​GPT Image Series

​Qwen Series

​FAQ

Introduction

Authentication

Request Parameters

Basic Examples

Model-Specific Parameters

Doubao Seedream

GPT Image

Gemini

Supported Models

Gemini Series

Doubao Seedream Series

GPT Image Series

Qwen Series

FAQ