AI Image Generation API

Generate images from text prompts using FLUX.1, FLUX.2, Stable Diffusion, and Ideogram through a single API. One API key, one endpoint, eight model families — no GPU management.

Available models

Model	Speed	Quality	Features
FLUX.1 Schnell	Fast	Good	Text-to-image, best for prototyping
FLUX.1 Dev	Medium	High	Open weights, img2img support
FLUX.1 Pro	Medium	Very High	Production-grade
FLUX.1.1 Pro	Medium	Very High	Updated Pro model
FLUX.2 Pro	Medium	Highest	Up to 4MP, multi-reference images
FLUX Kontext	Medium	High	Image editing with text instructions
Stable Diffusion 3.5	Medium	High	Open weights
Ideogram v2	Medium	High	Best text rendering in images

Basic text-to-image

curl https://api.runcrate.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer rc_live_YOUR_API_KEY" \
  -d '{
    "model": "black-forest-labs/FLUX.1-schnell",
    "prompt": "A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background",
    "aspect_ratio": "1:1"
  }'

from openai import OpenAI

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

response = client.images.generate(
    model="black-forest-labs/FLUX.1-schnell",
    prompt="A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background",
)

print(response.data[0].url)

from runcrate import Runcrate

client = Runcrate(api_key="rc_live_YOUR_API_KEY")

image = client.models.generate_image(
    model="black-forest-labs/FLUX.1-schnell",
    prompt="A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background",
)

# Save directly to disk
image.data[0].save("earbuds.png")

import Runcrate from '@runcrate/sdk';

const rc = new Runcrate({ apiKey: 'rc_live_YOUR_API_KEY' });

const image = await rc.models.generateImage({
  model: 'black-forest-labs/FLUX.1-schnell',
  prompt: 'A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background',
});

// Save directly — handles base64, data URIs, and URLs
await image.save('earbuds.png');

import { runcrate } from '@runcrate/ai';
import { generateImage } from 'ai';

const { image } = await generateImage({
  model: runcrate.imageModel('black-forest-labs/FLUX.1-schnell'),
  prompt: 'A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background',
  size: '1024x1024',
});

console.log(image.base64);

Image editing with FLUX Kontext

FLUX Kontext models accept an existing image and a text instruction describing the edit. Pass a file path, URL, or base64 string as the image parameter.

from runcrate import Runcrate

client = Runcrate(api_key="rc_live_YOUR_API_KEY")

# Edit an existing image with a text instruction
edited = client.models.generate_image(
    model="black-forest-labs/FLUX.1-kontext-pro",
    prompt="Change the background to a tropical beach at sunset",
    image="./product-photo.png",  # file path (auto base64-encoded)
)

edited.data[0].save("product-beach.png")

import Runcrate from '@runcrate/sdk';

const rc = new Runcrate({ apiKey: 'rc_live_YOUR_API_KEY' });

const edited = await rc.models.generateImage({
  model: 'black-forest-labs/FLUX.1-kontext-pro',
  prompt: 'Change the background to a tropical beach at sunset',
  image: './product-photo.png',  // file path (auto base64-encoded)
});

await edited.save('product-beach.png');

The image field accepts three formats:

File path — "./photo.png" (auto-detected, read and base64-encoded)
URL — "https://..." (passed through as-is)
Base64 string — raw base64 data (passed through as-is)

Batch generation — product catalog

Generate a full set of product images in one script. This example creates hero images for an e-commerce catalog:

from runcrate import Runcrate

client = Runcrate(api_key="rc_live_YOUR_API_KEY")

products = [
    {"name": "Running Shoe", "prompt": "A sleek running shoe, white background, studio lighting"},
    {"name": "Backpack", "prompt": "A modern laptop backpack, minimalist, product photography"},
    {"name": "Watch", "prompt": "A luxury watch on marble surface, soft shadows"},
]

for product in products:
    image = client.models.generate_image(
        model="black-forest-labs/FLUX.1-schnell",
        prompt=product["prompt"],
    )
    filename = f"{product['name'].lower().replace(' ', '-')}.png"
    image.data[0].save(filename)
    print(f"Saved {filename}")

For higher throughput, run generations in parallel:

from runcrate import Runcrate
from concurrent.futures import ThreadPoolExecutor

client = Runcrate(api_key="rc_live_YOUR_API_KEY")

products = [
    {"name": "Running Shoe", "prompt": "A sleek running shoe, white background, studio lighting"},
    {"name": "Backpack", "prompt": "A modern laptop backpack, minimalist, product photography"},
    {"name": "Watch", "prompt": "A luxury watch on marble surface, soft shadows"},
    {"name": "Sunglasses", "prompt": "Designer sunglasses on a reflective surface, dramatic lighting"},
    {"name": "Headphones", "prompt": "Over-ear headphones floating, dark background, rim lighting"},
]

def generate(product):
    image = client.models.generate_image(
        model="black-forest-labs/FLUX.1-schnell",
        prompt=product["prompt"],
    )
    filename = f"{product['name'].lower().replace(' ', '-')}.png"
    image.data[0].save(filename)
    print(f"Saved {filename}")

with ThreadPoolExecutor(max_workers=5) as pool:
    pool.map(generate, products)

print("All product images generated.")

Parameters reference

Parameters vary by model. These are the most common:

Parameter	Type	Description
`model`	string	Model ID (required)
`prompt`	string	Text description of the image (required)
`aspect_ratio`	string	Output ratio: `1:1`, `16:9`, `9:16`, `4:3`, `3:2`
`seed`	integer	Reproducibility seed (omit for random)
`num_inference_steps`	integer	Number of diffusion steps — more steps = more detail, slower
`guidance`	number	How closely to follow the prompt
`negative_prompt`	string	What to avoid in the image

Model-specific parameters

FLUX Kontext models: Accept image for image editing
FLUX Canny: Requires control_image for edge-guided generation
FLUX.2 Pro: Accepts up to 8 input_images for reference-based generation
FLUX Dev/Krea: Accept image for img2img mode with prompt_strength control

Check the Playground to see the exact parameters available for each model.

Next.js API route

Add image generation to a web app with a single API route:

// app/api/generate-image/route.ts
import { runcrate } from '@runcrate/ai';
import { generateImage } from 'ai';

export async function POST(req: Request) {
  const { prompt, model, aspectRatio } = await req.json();

  const { image } = await generateImage({
    model: runcrate.imageModel(model || 'black-forest-labs/FLUX.1-schnell'),
    prompt,
    size: aspectRatio === '16:9' ? '1792x1024' : '1024x1024',
  });

  return Response.json({ image: image.base64 });
}

Call it from the frontend:

const response = await fetch('/api/generate-image', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    prompt: 'A mountain landscape at golden hour',
    model: 'black-forest-labs/FLUX.1-schnell',
    aspectRatio: '16:9',
  }),
});

const { image } = await response.json();
// image is a base64 string — render it in an <img> tag

Response format

All image generation requests return the same shape:

{
  "data": [
    {
      "url": "https://...",
      "b64_json": "..."
    }
  ]
}

The response includes either a url to the generated image or b64_json base64-encoded image data. The Runcrate SDKs provide a .save() helper that handles both formats automatically.

Pricing

Image generation pricing varies by model. FLUX.1 Schnell starts at ~$0.003/image. Higher-quality models like FLUX.2 Pro cost more per generation. Check the Model Catalog for current per-model pricing.

Inference Examples

Compute Examples

Storage Examples

AI Image Generation API

Available models

Basic text-to-image

Image editing with FLUX Kontext

Batch generation — product catalog

Parameters reference

Model-specific parameters

Next.js API route

Response format

Pricing

​Available models

​Basic text-to-image

​Image editing with FLUX Kontext

​Batch generation — product catalog

​Parameters reference

​Model-specific parameters

​Next.js API route

​Response format

​Pricing

Available models

Basic text-to-image

Image editing with FLUX Kontext

Batch generation — product catalog

Parameters reference

Model-specific parameters

Next.js API route

Response format

Pricing