fal-ai — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fal-ai (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Owner: Appie-2 (CMO) Created: 2026-04-07 Purpose: Access 600+ generative AI models for images, video, voice, and more — pay per use
A unified API gateway to 600+ generative AI models. No GPU management, no subscriptions, no idle costs. Pay per use.
Website: https://fal.ai Pricing: Pay-per-use (no subscription required)
# Install fal client
pip install fal-client
# Or use REST API directly
curl -X POST https://queue.fal.run/fal-ai/flux-pro/v1.1 \
-H "Authorization: Key YOUR_FAL_KEY" \
-d '{"prompt": "your prompt", "image_size": "landscape_16_9"}'Get your API key: https://fal.ai/dashboard/api-keys
| Model | Best For | Cost per Image |
|---|---|---|
| FLUX Pro | General purpose, high quality | ~$0.05-0.09 |
| FLUX Realism | Photorealistic images | ~$0.05-0.09 |
| Stable Diffusion 3.5 | Versatile, creative | ~$0.003-0.02 |
| Ideogram 3 | Text in images (logos, posters) | ~$0.01-0.05 |
| Recraft V3 | Design-focused, illustrations | ~$0.01-0.03 |
Sizes: square (1:1), portrait (2:3), landscape (3:2), 9:16, 16:9, A4 portrait, A4 landscape
| Model | Best For | Cost |
|---|---|---|
| Hailuo MiniMax Video | Text-to-video, motion | ~$0.26/5-sec 720p |
| Vidu | High quality video | ~$0.20-0.50/video |
| Kling | Motion control, camera movement | ~$0.30-0.60/video |
| Wan 2.1 | Open source video | ~$0.10-0.30/video |
Video with audio: +$0.20-0.40 per clip
| Model | Best For |
|---|---|
| MiniMax Speech | Voice cloning, natural TTS |
| F5 TTS | Fast, multilingual TTS |
import fal_client
# Generate an image
result = fal_client.run("fal-ai/flux-pro/v1.1", arguments={
"prompt": "Professional photo of a smartwatch on white marble surface, studio lighting",
"image_size": "square_hd",
"num_inference_steps": 28
})
image_url = result["images"][0]["url"]
# Generate video
result = fal_client.run("fal-ai/hailuo-minimax-video/v2", arguments={
"prompt": "A robot walking through a neon-lit city at night",
"duration": 5,
"resolution": "720p"
})
video_url = result["video"]["url"]
# Image-to-video (animate an image)
result = fal_client.run("fal-ai/minimax-video-01-live", arguments={
"image_url": "https://example.com/image.jpg",
"prompt": "Cinematic zoom in, camera slowly moves forward"
})You: "Create a promotional Instagram post for our new web design service"
Appie:
1. Writes caption using Content Genome (Hook + Authority + CTA)
2. Generates image: fal_client.run("fal-ai/flux-pro/v1.1", prompt="Modern web design dashboard on laptop, dark theme, teal accents")
3. Adds text overlay with service name
4. Formats for Instagram (1080x1080)
5. Schedules via Zernio for optimal posting time
6. Updates Notion content calendar
Cost: ~$0.05 | Time: ~2 minutes| Tip | Savings |
|---|---|
| Use SD 3.5 for drafts, FLUX Pro for final | 5-10x cheaper |
| Reuse prompts (iterate, don't regenerate) | ~50% savings |
| Batch generation (run 5 at once) | Faster, more efficient |
| Use Wan 2.1 (open source) for testing | Free |
Get started: https://fal.ai — No subscription needed, pay per use.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.