Runflow
Black Forest Labs

FLUX.1 [pro] v1.1 API

FLUX.1 [pro] v1.1 — 12B-param commercial-grade model by Black Forest Labs. 6× faster than v1, highest benchmark Elo. $0.04/MP.

flux-pro-v1-112B paramsRectified Flow Transformer
Updated March 2026·Early access
Price
$0.04/MP
Per megapixel · ~$0.04 for 1024×1024
Speed
6× faster
Than original FLUX.1 [pro]
Cold Start
5–10s
Not billed, handled by Runflow
Parameters
12B
Rectified Flow Transformer

FLUX.1 [pro] model family by Black Forest Labs

Multiple FLUX Pro variants for different quality and resolution needs — all on the same Runflow API.

FLUX.1 [pro] v1.1

This model

Commercial-grade — 6× faster, highest Elo, $0.04/MP

FLUX.1 [pro] v1.1 Ultra

Ultra

4MP high-res output with integrated upscaling and raw mode, $0.06/image

FLUX.1 [dev]

Open

Open-weight, 12B params, $0.025/MP — non-commercial license

FLUX.1 [schnell]

Speed

Speed-optimised — sub-second at $0.003/MP, Apache 2.0

Benchmarked for your use case

Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.

Use CaseAssessmentNotes
PortraitStrongEnhanced composition and fine detail — top Elo among commercial models
FashionStrongSuperior multi-subject coherence for editorial scenes
ProductStrongSharp detail rendering with accurate lighting
CreativeStrongImproved text-in-image capabilities and artistic fidelity

API Parameters

Full parameter reference for the flux-pro-v1-1 model endpoint.

ParameterTypeDescription
promptstringText description of the image to generate.
image_sizeobject | stringOutput size. Presets: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Or custom {width, height}. Default: landscape_4_3.
num_imagesintegerNumber of images to generate per request. Range: 1–4. Default: 1.
output_formatstringOutput format. Options: "jpeg", "png". Default: "jpeg".
safety_tolerancestringContent moderation strictness. 1 = most strict, 6 = most permissive. Default: 2.
enhance_promptbooleanAutomatically enhance the prompt for better results. Default: false.
seedintegerRandom seed for reproducible outputs.
sync_modebooleanReturn media as data URI without storing in request history. Default: false.

Technical Specifications

ArchitectureRectified Flow Transformer
Parameters12 billion
Max Resolution2048 × 2048
Speed6× faster than FLUX.1 [pro] v1.0
Max Batch Size4 images per request
Output FormatsJPEG · PNG
Prompt EnhancementOptional — automatic prompt refinement
LicenseCommercial

Why run FLUX.1 [pro] v1.1 on the Runflow API

Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.

Highest benchmark Elo

FLUX.1 [pro] v1.1 achieved the highest overall Elo score on the Artificial Analysis image arena — beating all commercial models at launch.

6× faster than v1

Dramatically reduced inference time over the original FLUX.1 [pro] while improving composition, detail, and text-in-image quality.

Enhanced multi-subject coherence

Noticeably better at complex scenes with multiple people, objects, or architectural elements — fewer artefacts and more natural spatial relationships.

Optional prompt enhancement

The enhance_prompt parameter automatically refines your input for better results — useful when working with short or ambiguous prompts.

Sentinel quality scoring

Every output is scored by Runflow's Sentinel system before delivery, catching low-quality or off-prompt results automatically.

Explore other models

Same API, different strengths. Switch models with one parameter change.

Frequently asked questions

Resources

Start generating images with FLUX.1 [pro] v1.1

Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.