AI Image Generator API — batch text to image (FLUX), pay per image

Give it one prompt or a thousand, get one image per prompt (or up to four variations) generated with FLUX.2 Klein 9B, one dataset item per image: the image URL, its width, height and seed, or a clear error. No API key, no GPU, no subscription. $0.02 per image delivered (1024×1024 included), failures are free.

Built for automation and AI agents: send a list in prompts, or one prompt (or a newline-separated string) in prompt; every alias (prompts, prompt, texts, queries) is merged, nothing is required, and the default input runs on its own so you can see the output shape before sending your own prompts.

Pairs with Image Upscaler API (enlarge the result to print size) and Background Remover API (cut the subject out).

What you get

One item per generated image, in your dataset:

{
  "index": 0,
  "variant": 0,
  "prompt": "A ceramic coffee mug on a wooden table, soft morning light, product photography",
  "outputUrl": "https://api.apify.com/v2/key-value-stores/abc123/records/image-0000-0.png",
  "width": 1024,
  "height": 1024,
  "seed": 674885436,
  "model": "fal-ai/flux-2/klein/9b",
  "format": "png",
  "durationMs": 6200,
  "status": "ok",
  "error": null
}

A prompt that fails, or an image flagged by the safety checker, comes back with "status": "error" and the reason in error. It is never charged. Pass the seed back with the same prompt to reproduce an image.

Use cases

• Generate product mock-ups, hero images and illustrations for landing pages in bulk.
• Produce one image per article, post or ad variant from a content calendar.
• Create thumbnails and social visuals straight from an n8n / Make / Zapier flow.
• Give an AI agent a single call that turns a list of ideas into a list of images.

Input

Field	Type	Default	Notes
prompts	array	two sample prompts	English works best. For one prompt or a newline-separated string, use prompt.
prompt, texts, queries	aliases	—	Merged with prompts.
imageSize	preset	square_hd	square_hd 1024×1024, landscape_4_3 1024×768, landscape_16_9 1024×576, portrait_4_3, portrait_16_9, square 512×512.
width, height	integer	—	Exact pixels (256 to 2048), override imageSize when both are given.
quality	standard, fast	standard	standard = FLUX.2 Klein 9B; fast = FLUX Schnell, about twice as fast, for drafts.
imagesPerPrompt	1 to 4	1	Variations per prompt; each image is charged.
outputFormat	png, jpeg, webp	png
seed	integer	random	Fix it to reproduce an image.
maxPrompts	integer	100	Stop after this many prompts.

Minimal call:

{ "prompts": ["A red bicycle leaning on a brick wall, golden hour", "Isometric icon of a cloud server, flat design"] }

Pricing

• Image generated — $0.02 per image delivered, output up to 1024×1024 included.
• Extra megapixel — $0.01 per started megapixel above 1.1 MP for custom sizes (2048×2048 is 4.2 MP, so 3 extra).
• Failed prompts and safety-flagged images: free.

Set a maximum cost per run in Apify and the Actor stops cleanly when it is reached; remaining prompts are reported, not processed.

Via API, n8n, Make or MCP

Call it like any Apify Actor: POST https://api.apify.com/v2/actors/sherwood~image-generator-batch/run-sync-get-dataset-items with the JSON input above, or add it as a tool through the Apify MCP server. Results are plain dataset items, so get-dataset-items returns the URLs directly.

Limits

• Generation time is typically 4 to 10 seconds per image; 4 prompts are processed in parallel.
• A safety checker is always on: prompts producing unsafe content return an error item instead of an image.
• Output files live in the run's key-value store and follow your account's data retention.