Skip to main content
Endpoint: POST https://fal.run/fal-ai/flux-pro/v1.1-ultra Endpoint ID: fal-ai/flux-pro/v1.1-ultra

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Input Schema

string
required
The prompt to generate an image from.
integer
The same seed and the same prompt given to the same version of the model will output the same image every time.
boolean
default:"false"
If True, the media will be returned as a data URI and the output data won’t be available in the request history.
integer
default:"1"
The number of images to generate. Default value: 1Range: 1 to 4
OutputFormatEnum
default:"jpeg"
The format of the generated image. Default value: "jpeg"Possible values: jpeg, png
SafetyToleranceEnum
default:"2"
The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Default value: "2"Possible values: 1, 2, 3, 4, 5, 6
boolean
default:"false"
Whether to enhance the prompt for better results.
string
The image URL to generate an image from.
float
default:"0.1"
The strength of the image prompt, between 0 and 1. Default value: 0.1Range: 0 to 1
Enum | string
default:"16:9"
The aspect ratio of the generated image. Default value: 16:9Possible values: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21
boolean
default:"false"
Generate less processed, more natural-looking images.

Output Schema

list<registry__image__fast_sdxl__models__Image>
required
The generated image files info.
Timings
required
integer
required
Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.
list<boolean>
required
Whether the generated images contain NSFW concepts.
string
required
The prompt used for generating the image.

Input Example

Output Example

Black Forest Labs’ FLUX1.1 [pro] ultra delivers up to 2K resolution (4 megapixels) image generation at $0.06 per image. With 4x the resolution detail, this model extends FLUX1.1 [pro]‘s capabilities with enhanced photorealism while maintaining ~10 second generation times. Built for production workflows where resolution and visual fidelity directly impact deliverables. Use Cases: High-resolution marketing assets | Product photography | Editorial illustrations

Performance

At $0.06 per image with 4-megapixel output capability, FLUX1.1 [pro] ultra positions between standard-resolution alternatives and premium high-res solutions.

Professional-Grade Resolution Without Compromise

FLUX1.1 [pro] ultra extends Black Forest Labs’ architecture to 4-megapixel generation while maintaining the prompt interpretation and photorealism that defined the standard version. Where most high-resolution models sacrifice inference speed or introduce quality degradation, ultra mode processes at comparable latency to standard-resolution alternatives. What this means for you:
  • True 2K output: Generate up to 2048×2048 images without upscaling artifacts or post-processing, delivering print-ready assets directly from the API
  • Optional image conditioning: Use image_url and image_prompt_strength (0-1 range) to guide generation with reference images, enabling style transfer and composition control
  • Flexible aspect ratios: Support for multiple aspect ratios with automatic megapixel-based billing, pay only for the resolution you actually use
  • Granular safety controls: Six-level safety_tolerance parameter (1-6) lets you calibrate content filtering for your specific use case, from strict (1) to permissive (6)

Technical Specifications

API Documentation | Quickstart Guide | Enterprise Pricing

How It Stacks Up

**FLUX1.1 [pro] (0.05)FLUX1.1[pro]ultratradescostefficiencyfor4xresolutionat0.05)** – FLUX1.1 [pro] ultra trades cost efficiency for 4x resolution at 0.06 vs $0.05 (20% premium). Standard FLUX1.1 [pro] remains ideal for high-volume workflows where 1-megapixel output meets requirements and cost per image is the primary constraint. FLUX.1 Kontext [pro] ($0.05) – FLUX1.1 [pro] ultra prioritizes maximum resolution and photorealism for single-image generation. FLUX.1 Kontext [pro] emphasizes multi-image context understanding (up to 5 reference images) at standard resolution, optimized for workflows requiring consistent style or character preservation across generations. **AuraFlow (0.012)FLUX1.1[pro]ultradeliversprofessionalgradephotorealismand4megapixeloutputat5xthecost(0.012)** – FLUX1.1 [pro] ultra delivers professional-grade photorealism and 4-megapixel output at 5x the cost (0.06 vs $0.012). AuraFlow offers open-weight flexibility and cost efficiency for rapid iteration workflows where resolution and photorealism requirements are secondary to generation volume.

Limitations

  • num_images range: 1 to 4
  • output_format restricted to: jpeg, png
  • safety_tolerance restricted to: 1, 2, 3, 4, 5, 6
  • image_prompt_strength range: 0 to 1