FLUX.2 [klein] 4B is Black Forest Labs' fastest text-to-image model, a 4-billion-parameter distilled model released under the Apache 2.0 license. It generates images in as few as 4 inference steps, with sub-second latency on modern hardware, enhanced realism, crisper text rendering, and native editing capabilities from a single checkpoint. Suited to real-time apps, interactive workflows, rapid iteration, and high-volume generation.
FastRouter routes your requests to this provider. You can also bring your own key.
falaiRequest parameters you can send with this model.
OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.
<FASTROUTER_API_KEY> with your key · Get your key →Installblack-forest-labs/flux-devFLUX.1 [dev] is a 12 billion parameter text-to-image model developed by Black Forest Labs for high-quality image generation and editing from text prompts.It excels at generating photorealistic images with strong prompt adherence, real-world physics understanding (e.g., lighting, spatial relationships), and readable text rendering.
black-forest-labs/flux-kontext-proFLUX.1 Kontext [pro] is an advanced image generation and editing model from Black Forest Labs that supports both text prompts and reference images for in-context modifications.
black-forest-labs/flux-pro-2.0FLUX.2 Pro (also styled as Flux-2-Pro or FLUX.2 [pro]) is a production-grade AI image generation and editing model developed by Black Forest Labs, released in November 2025 as the flagship of the FLUX.2 family. It excels in creating high-quality, photorealistic images up to 4 megapixels from text prompts, with advanced controls for editing, multi-reference image use (up to 8 references), and precise outputs suitable for commercial workflows like product photography, UI prototyping, and brand design.
black-forest-labs/flux-schnellFLUX.1 [schnell] is a 12-billion-parameter rectified flow transformer model for text-to-image generation, developed by Black Forest Labs. "Schnell" (German for "fast") is the speed-optimized variant of the FLUX.1 model family, distilled for rapid inference — it can generate high-quality images in as few as 1–4 diffusion steps, making it significantly faster than typical diffusion models while maintaining strong prompt adherence and image fidelity.
Model scores sourced from ArtificialAnalysis