Room AI API

Build with AI-powered room design. Integrate 18 generation models into your application with a single REST endpoint.

Get API Key Quick Start

Quick Start

Get an API key

Make a request

POST to /api/v1/generate with your model and parameters.

Get the result

Receive a hosted image URL in the response. Images are hosted for 30 days.

bash

curl -X POST https://roomai.com/api/v1/generate \
  -H "Authorization: Bearer rai_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "interior",
    "image": "https://example.com/room.jpg",
    "styles": "modern",
    "knows": "living room"
  }'

Base URL

https://roomai.com/api/v1

Authentication

All API requests require an API key sent in the Authorization header as a Bearer token.

bash

curl -H "Authorization: Bearer rai_live_your_api_key_here" \
  https://roomai.com/api/v1/generate

API keys can be created and managed in the Developer Dashboard. Keys are shown once upon creation — store them securely.

Generators

18 AI models available through a single endpoint. Click a model to see its full documentation with parameters, examples, and tips.

Interior

Interior AIinterior

Redesign any room in 40+ styles

1 token

Fill Room AIfill

Fill empty rooms with AI-generated furniture

1 token

Exterior

Exterior AIexterior

Transform home exteriors with AI

1 token

Landscape AIlandscape

Generate landscape designs matched to location

1 token

Tools

AI Replacemagicwand

Replace specific furniture using a mask

1 token

Remove Furniture AIremovefurniture

Remove all furniture from a room

1 token

Photo Enhancer AIenhance

Upscale and enhance image quality (2x/4x/8x)

1 token

Remove Background AIremovebg

Remove image background

1 token

Change Background AIchangebg

Replace background with AI

1 token

Sketch AIsketch

Convert sketches to photorealistic renders

1 token

Magic Prompt AImagicprompt

Transform images using text prompts

1 token

Expand AIexpand

Extend cropped photos with AI outpainting

1 token

Pattern AIpattern

Generate seamless tileable textures

1 token

Vector AIvector

Export precise SVG vector drawings

1 token

3D

Render AIrender

Convert 3D screenshots to photorealistic renders

1 token

3DGen AI3dgen

Generate exportable 3D models from images

3 tokens

Video AIvideo

Create 3D flythrough video animations

10 tokens

Explore

Fluw AIfluw

Generate lifelike photos from prompts

2 tokens

POST /generate

The main generation endpoint. Send a model name and parameters to generate an image.

POST /api/v1/generate

Request Body

json

{
  "model": "interior",
  "image": "https://example.com/room.jpg",
  "styles": "modern",
  "knows": "living room",
  "prompt": "modern minimalist design",
  "precise": "50",
  "format": "png"
}

Response

json

{
  "status": "success",
  "result": {
    "image_url": "https://storage.googleapis.com/...",
    "model": "interior",
    "tokens_used": 1,
    "processing_time_ms": 4500
  }
}

GET /results

Optional endpoint for polling async generation results. The /generate endpoint handles polling server-side by default, but this endpoint is available if you want to manage polling yourself.

GET /api/v1/results?processing_url=https://...

Common Parameters

Parameters shared across most generators. See individual model pages for model-specific parameters.

Parameter	Type	Required	Description
`model`	string	Required	The generator model to use (see Generators above)
`image`	string	Required	URL of the input image (not needed for text-to-image models like fluw and pattern)
`prompt`	string	Optional	Text description of the desired output
`styles`	string	Optional	Design style (e.g. modern, minimalist, scandinavian). 99+ styles available.
`knows`	string	Optional	Room/building type (e.g. living room, bedroom, house exterior)
`precise`	string	Optional	AI strength from "0" to "100". Higher values preserve more of the original.
`format`	string	Optional	Output format — "png" (default)
`seed`	number	Optional	Random seed for reproducible results
`webhook`	string	Optional	URL for async result delivery (see Webhooks section)

Response Format

Success (200)

json

{
  "status": "success",
  "result": {
    "image_url": "https://...",
    "model": "interior",
    "tokens_used": 1,
    "processing_time_ms": 4500
  }
}

Error Codes

Code	Error	Description
400	`INVALID_MODEL`	Unknown model value
401	`UNAUTHORIZED`	Invalid or missing API key
402	`INSUFFICIENT_TOKENS`	Not enough tokens in your balance
429	`RATE_LIMIT_EXCEEDED`	Too many requests — retry after cooldown
500	`GENERATION_FAILED`	Generation failed — tokens refunded

Error Response Format

json

{
  "status": "error",
  "error": {
    "code": "INSUFFICIENT_TOKENS",
    "message": "Not enough tokens",
    "required": 1,
    "balance": 0
  }
}

Rate Limits

Each API key has a default rate limit of 60 requests per minute. If you exceed this limit, the API will return a 429 status with a retryAfter value in seconds.

Need higher limits? Contact us at api@roomai.com.

Code Examples

cURL

bash

curl -X POST https://roomai.com/api/v1/generate \
  -H "Authorization: Bearer rai_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "interior",
    "image": "https://example.com/room.jpg",
    "styles": "modern",
    "knows": "living room"
  }'

JavaScript / Node.js

javascript

const response = await fetch("https://roomai.com/api/v1/generate", {
  method: "POST",
  headers: {
    "Authorization": "Bearer rai_live_your_api_key",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "interior",
    image: "https://example.com/room.jpg",
    styles: "modern",
    knows: "living room",
  }),
});

const data = await response.json();

if (data.status === "success") {
  console.log("Image URL:", data.result.image_url);
  console.log("Tokens used:", data.result.tokens_used);
} else {
  console.error("Error:", data.error.message);
}

Python

python

import requests

response = requests.post(
    "https://roomai.com/api/v1/generate",
    headers={
        "Authorization": "Bearer rai_live_your_api_key",
        "Content-Type": "application/json",
    },
    json={
        "model": "interior",
        "image": "https://example.com/room.jpg",
        "styles": "modern",
        "knows": "living room",
    },
)

data = response.json()

if data["status"] == "success":
    print("Image URL:", data["result"]["image_url"])
else:
    print("Error:", data["error"]["message"])

Webhooks

For long-running generations (like Video AI), you can provide a webhook URL in your request. The API will return immediately with a job ID and POST the final result to your webhook URL when complete.

Request

json

{
  "model": "video",
  "image": "https://example.com/room.jpg",
  "webhook": "https://your-app.com/webhook/roomai"
}

Immediate Response

json

{
  "status": "processing",
  "jobId": "api_1234567890_abc123"
}

Webhook Payload

json

{
  "status": "success",
  "jobId": "api_1234567890_abc123",
  "result": {
    "image_url": "https://...",
    "model": "video",
    "tokens_used": 10,
    "processing_time_ms": 45000
  }
}

Webhook delivery is retried up to 3 times with exponential backoff on failure.

Image Hosting

Generated images are hosted on Firebase Storage and accessible via signed URLs. URLs expire after 30 days. Download and store images on your own infrastructure if you need them longer.