RailwailRailwail

Flux 1.1 Pro Ultra

Popular
Black Forest Labs
Image Generation

FLUX 1.1 Pro in ultra mode. Up to 4 megapixel images with raw mode for photorealism.

Generate with Flux 1.1 Pro Ultra
Describe what you want and pick a size — the image renders inline.
Sign in to try this model with €5 free credits.
Sign in
Result appears here
TL;DR·Last updated March 4, 2026

Flux 1.1 Pro Ultra is image generation AI model from Black Forest Labs, priced at €0.000 per 1M input tokens with a unknown context window.

Try Flux 1.1 Pro Ultra
Sign in to generate — 50 free credits on sign-up

Examples

See what Flux 1.1 Pro Ultra can generate

Sample output

Photorealistic Portrait

Prompt: "A close-up editorial portrait of an elderly fisherman with deep weathered wrinkles, bright blue eyes, wearing a cable-knit sweater, shot on medium format film with shallow depth of field, natural window light"

Sample output

Architecture

Prompt: "A stunning modern cliffside villa with floor-to-ceiling glass walls overlooking the Mediterranean Sea, infinity pool merging with the horizon, golden hour lighting, architectural photography style"

Sample output

Nature Macro

Prompt: "An extreme macro photograph of morning dew drops on a spider web, each droplet acting as a tiny lens refracting the sunrise behind it, bokeh background of wildflowers, National Geographic quality"

Pricing

Price per Generation
Per generation€0.60

API Integration

Use our OpenAI-compatible API to integrate Flux 1.1 Pro Ultra into your application.

Install
npm install railwail
JavaScript / TypeScript
import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

const images = await rw.run("flux-pro-ultra", "A beautiful sunset over Tokyo");
console.log(images[0].url);

// Or use the image() method for full control
const res = await rw.image("flux-pro-ultra", "A cat in space", {
  size: "1024x1024",
  n: 1,
});
console.log(res.data[0].url);
Specifications
Price
€0.60
Avg. latency
15.0s
Est. duration
15s
Developer
Black Forest Labs
Category
Image Generation
Supported Formats
jpg
png
Tags
high-quality
photorealistic

Deep dive — Black Forest Labs's Flux 1.1 Pro Ultra

About Black Forest Labs
Founded 2024 · Freiburg, Germany

Black Forest Labs was founded in August 2024 by Robin Rombach, Patrick Esser, Andreas Blattmann and Dominik Lorenz, the team that created Latent Diffusion at LMU Munich and Stable Diffusion at Stability AI. Headquartered in Freiburg, Germany, the lab raised a $31M seed round led by Andreessen Horowitz and has since released the FLUX.1 family and FLUX 1.1 series. FLUX 1.1 [pro] (released October 2024) and the higher-resolution FLUX 1.1 [pro] Ultra (released November 2024) are the flagship commercial tiers, available only through the Black Forest Labs API and partner platforms such as Replicate, fal.ai and Together AI.

Visit Black Forest Labs →
Architecture
Rectified-flow Diffusion Transformer (DiT) with native 4 MP rendering

FLUX 1.1 [pro] Ultra is Black Forest Labs' highest-quality commercial image model, released as an API-only tier in November 2024. It builds on the FLUX 1.1 [pro] backbone — a rectified-flow Diffusion Transformer trained with the flow-matching objective from the SD3 paper (Esser et al. 2024) — but is fine-tuned and architecturally extended to produce up to 4 megapixels (2048x2048 or 1568x2520) natively without tiling or super-resolution. Black Forest Labs reports that Ultra achieves these resolutions with the same speed as standard FLUX 1.1 [pro] thanks to architectural and inference optimisations including grouped attention, FP8 inference and improved noise schedules. A complementary 'Raw' mode is exposed that produces less stylised, more photographic outputs. The model uses T5-XXL plus CLIP-L text encoders, the standard 16x latent VAE and 28-50 flow-matching sampling steps.

Parameters
Undisclosed (substantially larger than 12B FLUX.1 backbone)
Context
512 tokens
What it can do
  • Native 4 MP rendering (up to 2048x2048 or 1568x2520)
  • State-of-the-art photorealism in the FLUX family
  • 'Raw' mode for unstylised photographic look
  • Strong typography for an image model
  • Excellent prompt adherence via T5-XXL
  • Fast inference (~10-20s per 4MP image)
  • Available via Black Forest Labs API, Replicate, fal.ai, Together AI
  • Best for: print-quality marketing, large-format ads, editorial photography, premium creative.
Training & License

Pretrained on a large licensed image-text corpus; fine-tuned at high resolutions for the Ultra tier. Exact data is not disclosed.

License: Proprietary commercial license via Black Forest Labs API and approved partners. Pay-per-image pricing.

Known limitations
  • API only, no open weights
  • Higher per-image cost than dev/schnell tiers
  • Generation latency higher than 1 MP modes
  • No fine-tuning for external customers

Research papers

Frequently asked questions

Related Models

View all Image Generation

Flux Dev

Black Forest Labs

Black Forest Labs' development model. Fast, high-quality image generation with LoRA support.

€0.50

Google Imagen 4

Google DeepMind

Google's Imagen 4. Text-to-image with strong photorealism and improved typography support.

€0.04

Google Imagen 4 Ultra

Google DeepMind

Premium Imagen 4 tier. Highest fidelity, prompt adherence and typography quality from Google.

€0.06

Ideogram 3.0

Ideogram

Ideogram's flagship text-to-image model with industry-leading text rendering and prompt adherence.

€0.09

Start using Flux 1.1 Pro Ultra today

Get started with free credits. No credit card required. Access Flux 1.1 Pro Ultra and 100+ other models through a single API.

Get Started FreeBrowse All Models