FLUX.1-dev
About FLUX.1-dev
FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. It offers cutting-edge output quality, second only to their state-of-the-art model FLUX.1 [pro]. The model features competitive prompt following, matching the performance of closed source alternatives. Trained using guidance distillation, FLUX.1 [dev] is more efficient. Open weights are provided to drive new scientific research and empower artists to develop innovative workflows
Available Serverless
Run queries immediately, pay only for usage
$
0.014
Per Image
Metadata
Specification
State
Available
Architecture
Calibrated
No
Mixture of Experts
No
Total Parameters
12
Activated Parameters
12 billion
Reasoning
No
Precision
FP8
Context length
0K
Max Tokens
Supported Functionality
Serverless
Supported
Serverless LoRA
Not supported
Fine-tuning
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported
JSON Mode
Not supported
Structured Outputs
Not supported
Tools
Not supported
Fim Completion
Not supported
Chat Prefix Completion
Not supported
Compare with Other Models
See how this model stacks up against others.

Qwen
text-to-image
Qwen-Image
Release on: Sep 15, 2025
$
0.042
/ Image

Qwen
image-to-image
Qwen-Image-Edit
Release on: Sep 18, 2025
$
0.04
/ Image

Black Forest Labs
text-to-image
FLUX.1 Kontext [pro]
Release on: Jul 11, 2025
$
0.04
/ Image

Black Forest Labs
text-to-image
FLUX.1 Kontext [max]
Release on: Jul 11, 2025
$
0.08
/ Image

Black Forest Labs
text-to-image
FLUX 1.1 [pro] Ultra
Release on: Jul 11, 2025
$
0.06
/ Image

Black Forest Labs
text-to-image
FLUX 1.1 [pro]
Release on: Jul 11, 2025
$
0.04
/ Image

Black Forest Labs
image-to-image
FLUX.1-Kontext-dev
Release on: Jun 27, 2025
$
0.015
/ Image

Black Forest Labs
text-to-image
FLUX.1-dev
Release on: Aug 1, 2024
$
0.014
/ Image

Black Forest Labs
text-to-image
FLUX.1-schnell
Release on: Aug 1, 2024
$
0.0014
/ Image
Model FAQs: Usage, Deployment
Learn how to use, fine-tune, and deploy this model with ease.
