Black Forest Labs AI API models
Black Forest Labs AI models on MuAPI
Explore Black Forest Labs models for chat, code, image and video generation, including Gemini, Nano Banana and Veo-style workflows available through MuAPI.
All models
37 ModelsVideo Generation Models
$0.350 / second
flux-3-text-to-video
FLUX 3 Text-to-Video generates cinematic video clips with optional native synchronized audio from a single unified model — the same architecture Black Forest Labs uses for FLUX 3's action-prediction research. Expect coherent motion, strong physical plausibility, and scene-appropriate ambient sound baked directly into generation.
$0.350 / second
flux-3-image-to-video
FLUX 3 Image-to-Video animates a still image into a cinematic clip with optional native synchronized audio, using Black Forest Labs' unified image/video/audio architecture. Motion stays physically grounded and consistent with the source frame, making it suited for product animation, portrait bring-to-life effects, and scene extension.
Image Generation Models
$0.013 / 1K tokens
flux-2-klein-9b
Flux-2-Klein-9B is a mid-size text-to-image model that balances detail quality and generation speed. It handles richer lighting, better textures, and more nuanced scenes than smaller variants, while still working well with clear, grounded prompts. Ideal for polished illustrations, product visuals, mascots, and everyday scenes with character.
$0.050 / 1K tokens
flux-3-text-to-image
FLUX 3 Text-to-Image is Black Forest Labs' next-generation multimodal frontier model, jointly trained across image, video, and audio for outputs that are truer to life in every style. It generates highly photorealistic and stylistically flexible images from text prompts, with sharper detail, more coherent composition, and stronger prompt adherence than the FLUX.2 generation.
$0.060 / generation
flux-3-image-to-image
FLUX 3 Image-to-Image edits and restyles existing images using a text instruction plus up to several reference images. Built on Black Forest Labs' unified multimodal architecture, it preserves subject identity and scene structure while applying precise, prompt-driven edits — ideal for product retouching, style transfer, and character-consistent edits.
$0.025 / 1K tokens
flux-3-dev
FLUX 3 Dev is the faster, lower-cost variant of Black Forest Labs' FLUX 3 frontier model, planned for open-weight release. It trades a small amount of peak fidelity for significantly reduced latency and price, making it well suited for rapid iteration, prototyping, and high-volume text-to-image generation.
$0.003 / 1K tokens
flux-schnell
Flux Schnell is a lightning-fast image generation model designed for rapid iterations. It delivers good visual quality from text prompts almost instantly, making it perfect for real-time concept testing, brainstorming, and UI-integrated experiences.
$0.015 / generation
flux-dev-lora
Enables text-to-image generation using custom LoRA models. Generate consistent characters, styles, or branded visuals with high quality and fast results.
$0.020 / generation
flux-kontext-dev-i2i
Takes an input images and transforms it based on a new prompt. Keeps structure or pose while changing style, appearance, or details.
$0.030 / generation
flux-kontext-pro-i2i
Flux Kontext Pro I2I variant enables transforming base images into refined artwork while keeping structure intact. It’s useful for sketch refinement, visual style changes, and creative edits such as re-dressing, relighting, or re-theming with prompt guidance.
$0.040 / generation
flux-pulid
Flux PuLID is an innovative image-to-image model that enables consistent face rendering across different styles or scenes—without needing any model fine-tuning. By providing a reference image (e.g., a portrait), the model generates new visuals while maintaining your subject’s identity with high fidelity.
$0.010 / generation
flux-redux
Flux Redux is a transformation model that reimagines or enhances your input images while preserving their main structure and subject. It’s built for creative refinement — whether you want style transfer, artistic reinterpretation, cinematic polish, or mood transformation.
$0.090 / 1K tokens
flux-2-flex
Flux-2-Flex Text-to-Image is a flexible, high-fidelity generative model capable of producing detailed, imaginative, and stylistically rich scenes from text alone. It excels at surreal concepts, fantasy environments, sci-fi structures, cinematic atmospheres, and high-resolution artistic compositions with strong prompt adherence.
$0.032 / generation
flux-2-pro-edit
Flux-2-Pro Edit enables precise, high-fidelity modifications to an existing image while preserving its lighting, style, mood, and composition. It’s ideal for replacing objects, altering materials, adjusting environmental elements, or performing stylistic transformations without damaging the original scene’s quality. Flux-2-Pro maintains ultra-detailed textures and cinematic realism during edits.
$0.006 / 1K tokens
flux-2-klein-9b-turbo
Flux-2-Klein-9B Turbo is a high-performance, mid-size text-to-image model. This distilled variant of Klein 9B provides a superior balance of speed and detail, delivering richer textures and complex scenes with significantly reduced generation times. Ideal for polished illustrations and character-rich visuals where performance is key.
$0.040 / generation
flux-kontext-effects
Flux Kontext Effects is a creative image and video model that applies stylized transformations, cinematic filters, and artistic reinterpretations to your inputs. Instead of generating new content from scratch, it enhances or reimagines existing images and videos with unique looks — ranging from surreal effects to realistic cinematic moods.
$0.031 / generation
flux-2-dev-edit
Flux 2 Dev Edit takes an existing image and applies transformations, replacements, or style changes based on a text instruction. It preserves composition, lighting, and the overall scene while modifying only what the edit prompt specifies. Ideal for creative replacements, stylistic adjustments, object swaps, and environment changes while keeping the original artistic integrity.
$0.008 / generation
flux-2-klein-4b-turbo-edit
Flux-2-Klein-4B Turbo Edit provides ultra-fast, instruction-based image editing. This high-efficiency variant of Klein 4B Edit is optimized for near-instant swaps and tweaks while preserving layout and lighting. Ideal for real-time design tools and quick creative adjustments.
$0.020 / 1K tokens
flux-2-klein-4b-text-to-image-lora
Flux-2-Klein-4B Text-to-Image with LoRA pairs the lightweight Klein 4B model with custom LoRA adapters so you can dial in specific styles, characters, or aesthetics. Ideal for stylized branding, character art, and personalized look-and-feel without retraining a base model.
$3.200 / generation
flux-lora-trainer
Train a custom Flux LoRA from your own images. Upload a .zip of 10-50 photos (and optional captions) with a trigger phrase, and receive a portable .safetensors file you can plug into any Flux Dev pipeline for consistent subjects, characters, or styles.
$0.030 / 1K tokens
flux-kontext-pro-t2i
Flux Kontext Pro T2I offers fast and reliable generation with creative flexibility. It supports stylized prompts, character design, and fantasy themes while maintaining clear subject coherence.
$0.060 / 1K tokens
flux-kontext-max-t2i
Flux Kontext Max T2I delivers photorealistic or cinematic-quality images with exceptional detail. It's optimized for high-end visuals — from realistic humans to polished product renders.
$0.060 / generation
flux-kontext-max-i2i
Flux Kontext Max I2I in Max mode allows precise image enhancement and visual transformations while retaining the source layout. It’s powerful for retouching, photo-to-art workflows, concept refinement.
$0.015 / 1K tokens
flux-dev
Generate stunning visuals from simple text prompts. Flux Dev transforms your ideas into high-quality, creative images using powerful AI vision models. Perfect for design, storytelling, concept art, and marketing.
$0.015 / 1K tokens
flux-krea-dev
Flux Krea Dev is a text-to-image model built by Black Forest Labs in collaboration with Krea AI, designed to generate highly photorealistic images that avoid the common 'AI look' artifacts (plastic skin, overexposed lighting, synthetic textures). It emphasizes real texture, natural lighting, and aesthetic control.
$0.015 / 1K tokens
flux-2-dev
Flux 2 Dev is a powerful text-to-image diffusion model designed for high-quality, fast, and highly detailed visual generation. It excels at creating cinematic lighting, vibrant compositions, surreal concepts, characters, products, and worlds with strong prompt following and artistic control. Ideal for rapid image ideation, visual storytelling, and concept art.
$0.090 / generation
flux-2-flex-edit
Flux-2-Flex Edit allows flexible transformation of an existing image: object replacement, material changes, lighting adjustments, style shifts, or localized edits. It preserves the original scene’s geometry, perspective, and lighting while modifying only what the edit prompt specifies.
$0.032 / 1K tokens
flux-2-pro
Flux-2-Pro Text-to-Image is a premium, high-fidelity generative model capable of producing ultra-realistic, cinematic, and deeply detailed images from text prompts. It excels at complex lighting, layered compositions, surreal visual concepts, and professional art-grade rendering suitable for concept art, advertising visuals, and world-building.
$0.010 / 1K tokens
flux-2-klein-4b
Flux-2-Klein-4B is a lightweight, fast text-to-image model optimized for clear subject rendering, good prompt adherence, and efficient generation. It works best with simple compositions, everyday scenes, and cute or friendly visuals, making it ideal for UI graphics, demos, thumbnails, mascots, and quick creative iterations.
$0.016 / generation
flux-2-klein-4b-edit
Flux-2-Klein-4B Edit applies lightweight, instruction-based edits to an existing image. It’s best for clear object swaps, small visual changes, and cute enhancements while preserving the original scene’s layout and lighting. Ideal for fast edits, UI demos, and simple creative tweaks.
$0.021 / generation
flux-2-klein-9b-edit
Flux-2-Klein-9B Edit performs higher-quality image edits with better detail retention, lighting consistency, and texture handling compared to smaller variants. It’s well-suited for cute character edits, object additions, and visual refinements that need to look natural and polished while keeping the original scene intact.
$0.005 / 1K tokens
flux-2-klein-4b-turbo
Flux-2-Klein-4B Turbo is an ultra-fast, high-efficiency text-to-image model. It is a distilled version of the Klein 4B model, designed for near-instant rendering while maintaining impressive adherence to prompts. Perfect for rapid prototyping, real-time creative tools, and applications where speed is paramount.
$0.010 / generation
flux-2-klein-9b-turbo-edit
Flux-2-Klein-9B Turbo Edit offers high-quality, ultra-fast image editing with superior detail retention. This high-efficiency version of Klein 9B Edit handles lighting and textures with precision while delivering edits much faster than the standard variant. Best for polished character edits and professional refinements where speed is critical.
$0.025 / 1K tokens
flux-2-klein-9b-text-to-image-lora
Flux-2-Klein-9B Text-to-Image with LoRA combines the higher-fidelity Klein 9B base with custom LoRA adapters for richer textures and lighting under a chosen style. Ideal for premium stylized illustrations, branded character art, and polished marketing visuals.
$0.025 / generation
flux-2-klein-4b-edit-lora
Flux-2-Klein-4B Edit with LoRA performs instruction-based image edits while applying custom LoRA adapters, letting you preserve scene layout and lighting while pushing the result toward a specific style or character look. Great for stylized object swaps and look-conditioned edits.
$0.030 / generation
flux-2-klein-9b-edit-lora
Flux-2-Klein-9B Edit with LoRA delivers higher-fidelity, instruction-based edits combined with custom LoRA adapters. Best for premium stylized edits where lighting, textures, and identity must be preserved while applying a specific look.
$0.020 / 1K tokens
flux-kontext-dev-t2i
Generates an image from a text prompt, with optional reference image for pose or style guidance. Ideal for controlled, consistent image creation using just a description.