FLUX 3 Image
FLUX 3 Image is the image generation and editing model of Black Forest Labs’ FLUX 3 family, released on October 1, 2026. One endpoint generates or edits images, takes up to ten reference images and bounding-box layouts in the prompt, and outputs up to 4K (about 16 megapixels). Black Forest Labs also licenses the weights commercially for companies that run it on their own infrastructure.
Released
October 1, 2026
Type
image
License
proprietary
Context
—
Pricing
Per image, by resolution tier: 768sq $0.041; 1k (about 1 MP) $0.048; 1.5k (about 2 MP) $0.07; 2k (about 4 MP) $0.10; 4k (about 16 MP) $0.607. 1 credit = $0.01. Same price for API and Playground.
As the developer's own pages state it, checked . Not listed on the pricing page, which compares US dollar prices per million tokens.
Capabilities
Sources
Every figure on this page was checked against these pages on . A figure we could not source is left out.
- BFL docs: Release notes (FLUX 3 Image, 2026-10-01) (opens in a new tab)
- BFL docs: Pricing (opens in a new tab)
- BFL: FLUX 3 Image model page (opens in a new tab)
- BFL blog: FLUX 3 announcement (2026-07-23) (opens in a new tab)
Spotted something out of date? Tell us.
Links
In the news: FLUX 3 Image and Black Forest Labs
MarkTechPost
Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120
Black Forest Labs (BFL), a research entity known for its FLUX image models, has launched FLUX 3 Action, a 7-billion parameter open-weights World Action Model (WAM) designed for robot control applications. This model processes camera frames, robot state information, and textual instructions to predict future video frames and subsequent action sequences. On the RoboLab-120 benchmark, FLUX 3 Action achieved a task success rate of 42.92%, securing the top position. Deployment of FLUX 3 Action is feasible, though it has specific hardware requirements. The DROID policy necessitates approximately 32 GB of GPU memory when operating in BF16 precision on an H200 GPU. For systems with 24 GB graphics cards, it can be utilized with FP8 quantization and offloading of the text encoder. The FLUX Kommunity License permits non-commercial use of the model. Open robot policies often involve trade-offs between prediction accuracy and computational cost. For instance, NVIDIA's Cosmos 3 Nano, another WAM, leads RoboLab with a 36.8% success rate but is computationally intensive due to its video prediction capabilities. Conversely, Vision-Language Agents (VLAs) like π0.5 are faster but achieve lower success rates, around 28.0%. BFL's internal measurements on a B200 GPU indicated that Cosmos 3 Nano (in FP8) requires approximately 4.7 times more processing time per second of robot motion compared to π0.5 (in BF16). FLUX 3 Action aims to bridge this performance gap by jointly predicting video and actions, employing a smaller backbone architecture and distillation techniques to enhance efficiency. The architecture of FLUX 3 Action is an extension of the multimodal FLUX 3 backbone. Its pretraining phase incorporated image, video, and audio data, with video data constituting over 95% of the training tokens. The model encodes text, video, and robot state inputs into tokens. The backbone then decodes future tokens into predicted video frames and action tokens that translate into robot actions. During midtraining, the dataset was balanced between pretraining data (36.95% of samples) and action-aligned video data (63.05%). This action data was sourced from game recordings, egocentric human hand videos, data from handheld grippers, and teleoperation across 14 different embodiments. The majority of the robot data utilizes a standardized 50-dimensional end-effector action space, referred to as EE50. The significance of pretraining is highlighted by BFL's findings: without it, training a DROID-only model resulted in performance below 1% on RoboLab. However, with pretraining, the same training protocol yielded an 11.6% success rate. The RoboLab-120 benchmark comprises 120 distinct tabletop tasks simulated in Isaac Sim, with each task undergoing 10 trials on a Franka robot setup styled after DROID.
MarkTechPost
Black Forest Labs Releases FLUX 3: A Multimodal Flow Model for Image, Video, Audio and Robot Action Prediction
Black Forest Labs (BFL) has released FLUX 3, a multimodal foundation model designed to learn from images, videos, and audio concurrently within a unified architecture. This marks the first FLUX model to integrate video, audio, and action prediction capabilities from a single set of model weights. The BFL research team posits that no single sensory modality provides a complete understanding of the world, viewing images as snapshots of spatial structure, video as a means to capture temporal dynamics, and audio as an indicator of causal relationships in mechanical events. By training on all these modalities simultaneously, BFL suggests that they mutually constrain each other, leading to more coherent and realistic outputs where sound aligns with physical actions and motion adheres to principles of mass. FLUX 3 is the first model developed entirely on this principle. The underlying methodology for FLUX 3 is BFL's Self-Flow technique, which was introduced in March 2026. Self-Flow aligns multimodal generation and understanding within a single architecture by combining a flow matching objective with a self-supervised feature reconstruction objective. The reference implementation of Self-Flow, available on GitHub under the Apache-2.0 license, utilizes SiT-XL/2 with per-token timestep conditioning. Its training regimen involves a 25% per-token mask ratio and employs self-distillation, where a teacher model at layer 20 distills knowledge to a student model at layer 8. The specific checkpoint released is an ImageNet 256x256 research model, distinct from the full FLUX 3 model. BFL has significantly increased compute and data resources to train FLUX 3 on video, images, and audio in parallel, building upon the established Self-Flow approach. FLUX 3 Video introduces the capability to generate video clips up to 20 seconds in length with native audio support in a single generation process. The model accommodates various input modalities for video generation, including text-to-video, image-to-video, and video-to-video transformations using a reference clip. It also supports keyframe-to-video generation for controlled scene transitions and generative video-audio continuation based on provided input video and audio. BFL has also detailed its multimodal capabilities, indicating that FLUX 3 can predict robot actions, suggesting applications in robotics and embodied AI. The model's architecture allows for the prediction of future states and actions based on observed multimodal inputs, enabling more sophisticated control and interaction with physical environments. The research team emphasizes the model's ability to generalize across different domains and tasks due to its comprehensive training on diverse data types.