# FLUX.1 Schnell Fast Text-to-Image

> FLUX.1 Schnell Fast Text-to-Image is a paid API for AI agents from fal.ai at fal.mpp.tempo.xyz, paid per call via MPP, $0.003/call, status healthy (last checked 2026-10-11, last successful call 2026-09-19).

Generates images from text prompts in 1-4 inference steps using the FLUX.1 [schnell] model for near-instant results

## Facts

- Endpoint: POST https://fal.mpp.tempo.xyz/fal-ai/flux/schnell?utm_source=zero.xyz
- Price: $0.003/call
- Payment: MPP
- Status: healthy
- Last checked: 2026-10-11
- Last successful call: 2026-09-19
- Success rate: 99% of calls made through Zero
- Rating: 4.7 / 5 from 18 reviews
- Activations on Zero: 483
- Provider: fal.ai
- Docs: https://fal.ai/docs
- Website: https://fal.ai
- Tags: image, video, flux, stable-diffusion, grok, generation, ai, media
- Canonical page: https://www.zero.xyz/c/fal-ai-schnell-4412b32c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qP_eapzWrKRJnbZjfUZ9o

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability fal-ai-schnell-4412b32c -d '<json body>'
```

Example prompt: Use FLUX schnell to generate a 1024x768 image of a serene mountain landscape with a clear blue sky and calm lake reflecting the peaks — 4 inference steps, 1 image, seed 42.

## When to prefer this

Choose FLUX.1 Schnell when speed is the priority and you need images generated in under a second with 1-4 inference steps. It is ideal for rapid prototyping, real-time applications, or high-volume generation where cost ($0.003/call) and latency matter more than maximum quality. Use FLUX.1 Dev or Pro variants when higher fidelity and detail are required.

## Known failure modes

- Invalid image dimensions (non-standard sizes may be rejected)
- Prompt too long or contains disallowed content (NSFW filter triggered)
- num_inference_steps outside supported range 1-4 causes error
- Network timeout if fal.ai backend is overloaded
- Invalid seed value or guidance_scale out of supported bounds

## How this service works

FLUX.1 [schnell] - Fast text-to-image (1-4 steps)

## Output

Returns a list of generated image objects each with a hosted URL, width, height, and content type, along with the resolved prompt, inference timing in seconds, per-image NSFW flags, and the seed used for reproducibility.

## Example request

```json
{
 "seed": 42,
 "prompt": "A beautiful sunset over rolling hills with golden light",
 "image_size": {
  "width": 512,
  "height": 512
 },
 "num_images": 1,
 "guidance_scale": 7.5,
 "num_inference_steps": 4
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fal-ai-schnell-4412b32c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fal.mpp.tempo.xyz](https://www.zero.xyz/host/fal.mpp.tempo.xyz/llms.txt)