{"company":{"name":"Fal","slug":"fal","website":"https://fal.ai","category":"ai-ml"},"question":"What has Fal shipped recently?","answer":"In the last 30 days, Fal shipped 93 tracked updates. The most recent was \"minimax/h3-max/relight\" on 2026-10-08.","window":{"days":30,"updateCount":93,"returned":50},"generatedAt":"2026-10-08T10:29:42.760Z","updates":[{"title":"minimax/h3-max/relight","summary":"Fal.ai introduced minimax/h3-max/relight, a model enabling AI-driven video relighting using a lighting sphere image while preserving subjects, motion, camera, and audio. Pricing is $0.05–$0.32 per second depending on resolution (480p to 2K).","date":"2026-10-08","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/minimax/h3-max/relight","publisher":"fal.ai"},{"title":"fal-ai/vidu/q4/reference-to-video","summary":"Fal introduced Vidu Q4, a generative video model that creates up to 16-second videos from up to 12 reference images and 3 voice clips while maintaining character, object, and voice consistency. The model supports resolutions up to 4K and includes a tiered pricing model starting at $0.0315 per second at 540p, with promotional rates valid until November 30, 2024.","date":"2026-10-07","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/vidu/q4/reference-to-video","publisher":"fal.ai"},{"title":"fal-ai/vidu/q4/image-to-video","summary":"Fal introduced Vidu Q4, a model that converts a single image into 3–16 second videos with native audio up to 4K resolution. The tool targets animating stills, product shots, and character scenes with dialogue. Promotional pricing runs until November 30, after which rates increase by roughly 30–50% depending on resolution.","date":"2026-10-07","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/vidu/q4/image-to-video","publisher":"fal.ai"},{"title":"mureka/api/generate/song","summary":"Fal introduced the mureka/api/generate/song endpoint, enabling users to generate songs from text prompts or lyrics with controls for style, vocals, and melody. Pricing ranges from $0.045 to $0.75 per request depending on the model variant, with commercial use explicitly supported.","date":"2026-10-07","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/mureka/api/generate/song","publisher":"fal.ai"},{"title":"mureka/api/generate/instrumental","summary":"Fal.ai introduced a new API endpoint, mureka/api/generate/instrumental, enabling users to generate instrumental music from text descriptions or uploaded references. The service supports multiple model versions with varying pricing tiers, starting at $0.045 per request for older models and up to $0.225 for the latest mureka-9.5. Outputs are commercial-use enabled and streamable.","date":"2026-10-07","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/mureka/api/generate/instrumental","publisher":"fal.ai"},{"title":"mureka/api/generate/lyrics","summary":"Fal.ai added a new lyrics-generation API endpoint to its mureka model suite, enabling users to generate original song lyrics and titles from text prompts. The endpoint costs $0.0135 per request and supports commercial use, with an example generating an indie-pop song about a night-shift watchmaker’s rooftop garden.","date":"2026-10-07","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/mureka/api/generate/lyrics","publisher":"fal.ai"},{"title":"mureka/api/generate/lyrics-video","summary":"Fal.ai introduced a new model endpoint, mureka/api/generate/lyrics-video, enabling users to create lyrics videos from generated or uploaded audio. The feature supports customizable layouts, aspect ratios, backgrounds, and lyric-row selection, with a cost of $0.15 per video and commercial-use rights.","date":"2026-10-07","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/mureka/api/generate/lyrics-video","publisher":"fal.ai"},{"title":"mureka/api/generate/podcast","summary":"Fal.ai introduced a new API endpoint, mureka/api/generate/podcast, that converts ordered conversation turns into podcast audio with customizable text and voice selections. The feature costs $0.1725 per minute and supports commercial use, with pricing and example outputs provided in the documentation.","date":"2026-10-07","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/mureka/api/generate/podcast","publisher":"fal.ai"},{"title":"google/nano-banana-2.1","summary":"Fal introduced google/nano-banana-2.1, a Google-developed text-to-image model on its platform, supporting up to 4K resolution, adjustable aspect ratios, and optional web search grounding. Pricing starts at $0.08 per image, with tiered rates for higher resolutions and optional add-ons like web search ($0.015) and high thinking ($0.002).","date":"2026-10-06","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/google/nano-banana-2.1","publisher":"fal.ai"},{"title":"google/nano-banana-2.1/edit","summary":"Fal introduced the Google Nano Banana 2.1 Edit API, enabling precise image-to-image transformations with text instructions while preserving identity, expressions, and scene geometry. Outputs support up to 4K resolution with optional video, audio, or PDF context, and commercial use is permitted.","date":"2026-10-06","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/google/nano-banana-2.1/edit","publisher":"fal.ai"},{"title":"mirelo-ai/sfx-v1/video-to-audio","summary":"Fal introduced mirelo-ai/sfx-v1, a new video-to-audio model enabling users to generate synced sound tracks from videos, similar to MMAudio. The model is available via Fal’s platform with a cost of $0.007 per second of output and per sample, supporting commercial use.","date":"2026-10-06","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/mirelo-ai/sfx-v1/video-to-audio","publisher":"fal.ai"},{"title":"meshy/v6-lite/retexture","summary":"Fal.ai introduced meshy/v6-lite/retexture, a new model enabling users to apply new textures to existing 3D models via text prompts or reference images, with optional PBR maps included. The service costs $0.30 per retextured model and supports multiple 3D file formats (GLB, GLTF, OBJ, FBX, STL, USDZ).","date":"2026-10-06","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/meshy/v6-lite/retexture","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-vsr","summary":"Fal introduced Kandinsky 6.0 VSR, a video super-resolution model that upscales and enhances videos with sharper detail and flicker-free frames. The model is available via Fal's platform with a pricing model of $0.00036 per unit (1 megapixel × frames at 5 inference steps) and supports commercial use.","date":"2026-10-06","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-vsr","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-pro/text-to-video","summary":"Fal.ai introduced Kandinsky 6.0 Pro, a high-resolution text-to-video model generating 5-second 480p clips at 50 inference steps for $1.35 per unit. The model emphasizes cinematic motion and precise prompt adherence, with commercial use permitted. Example outputs include a lighthouse keeper and puffin scene.","date":"2026-10-06","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-pro/text-to-video","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-pro/image-to-video","summary":"Fal introduced an image-to-video feature for its Kandinsky 6.0 Pro model, enabling users to convert a single image into a 5-second 480p video clip with controllable motion. The feature costs $1.40 per unit (50 inference steps) and supports commercial use.","date":"2026-10-06","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-pro/image-to-video","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-lite/image-to-video","summary":"Fal introduced Kandinsky 6.0 Lite, a model that converts static images into short, prompt-guided video clips with lightweight inference. The feature costs $0.17 per 5-second 480p video at 10 inference steps and supports commercial use. Example outputs show realistic animations like a fox turning a newspaper page with ambient café sounds.","date":"2026-10-06","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-lite/image-to-video","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-lite/text-to-video","summary":"Fal.ai introduced Kandinsky 6.0 Lite, a lightweight text-to-video model optimized for speed and prompt adherence. The model generates 5-second 480p videos at 10 inference steps for $0.16 per unit, with commercial use permitted. Example outputs include a parrot and dog baking a cake.","date":"2026-10-06","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-lite/text-to-video","publisher":"fal.ai"},{"title":"fal-ai/kandinsky6-vsr/lite","summary":"Fal introduced Kandinsky 6.0 VSR Lite, a lightweight video super-resolution model optimized for quick, cost-efficient upscaling. The model charges $0.00036 per megapixel-frame at 5 inference steps and supports commercial use via a playground API.","date":"2026-10-06","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/fal-ai/kandinsky6-vsr/lite","publisher":"fal.ai"},{"title":"fal-ai/marigold-v2","summary":"Fal introduced Marigold V2, a diffusion-based depth estimation model built on Qwen-Image-Edit, enabling colorized depth map generation from single images. The model is available via Fal's platform with a $0.03 per-image pricing and supports commercial use.","date":"2026-10-03","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/fal-ai/marigold-v2","publisher":"fal.ai"},{"title":"minimax/h3-max/recast","summary":"Fal introduced H3 Max Recast, a new feature enabling users to recast people in videos using reference photos while preserving motion, camera work, cuts, and audio. The feature is billed at $0.30 per second for 768p output and $0.45 per second for 1080p, with reference images included at no extra cost.","date":"2026-10-01","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/minimax/h3-max/recast","publisher":"fal.ai"},{"title":"xai/grok-imagine-video/v1.5/lite/image-to-video","summary":"Fal.ai introduced the xAI Grok Imagine Video 1.5 Lite model for image-to-video generation, enabling users to create videos from static images. The model is priced per second of output and per input image, with costs varying by resolution (e.g., $0.03/sec at 720p).","date":"2026-10-01","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/image-to-video","publisher":"fal.ai"},{"title":"xai/grok-imagine-video/v1.5/lite/text-to-video","summary":"Fal.ai introduced xAI's Grok Imagine Video 1.5 Lite, enabling text-to-video generation with commercial use rights. The model supports 480p ($0.02/sec), 720p ($0.03/sec), and 1080p ($0.14/sec) resolutions, with a 5-second 720p clip costing $0.15.","date":"2026-10-01","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/text-to-video","publisher":"fal.ai"},{"title":"minimax/h3-max-turbo/extend-video","summary":"Fal.ai introduced a new feature for its H3 Max Turbo model allowing users to extend existing videos by 1–15 seconds with prompt-guided footage. The feature supports resolutions from 480p to 2K and includes optional audio references. Pricing ranges from $0.025 to $0.16 per second of generated content.","date":"2026-10-01","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/minimax/h3-max-turbo/extend-video","publisher":"fal.ai"},{"title":"blackforestlabs/flux-3/text-to-image, details and endpoints","summary":"Fal introduced Flux 3, Black Forest Labs' newest text-to-image model, enabling detailed 2K and 4K image generation with improved text rendering and layout control. The model is available via Fal's API with a promotional rate of $0.024 per image (50% off) until October 8, rising to $0.048 thereafter.","date":"2026-10-01","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/blackforestlabs/flux-3/text-to-image","publisher":"fal.ai"},{"title":"blackforestlabs/flux-3/edit-image, details and endpoints","summary":"Fal introduced Flux 3 Image Edit, a new model enabling precise local image edits or multi-reference composition without altering the rest of the image. The model supports up to 10 reference images, text editing, and style transfer, with a flat $0.024 per image promotional rate (rising to $0.048 after October 8).","date":"2026-10-01","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/blackforestlabs/flux-3/edit-image","publisher":"fal.ai"},{"title":"ideogram/v4.5/edit, details and endpoints","summary":"Fal introduced Ideogram v4.5, enabling image edits with up to 4 reference images, optional masking, and a high-precision mode that preserves unchanged pixels. Pricing ranges from $0.008 to $0.22 per image depending on quality tier, with no size-based pricing changes.","date":"2026-09-30","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/ideogram/v4.5/edit","publisher":"fal.ai"},{"title":"ideogram/v4.5, details and endpoints","summary":"Fal.ai launched Ideogram v4.5, enhancing its image generation model with improved text rendering for posters and logos. The update introduces three pricing tiers: $0.03 per image for Low quality, $0.06 for Medium, and $0.22 for High quality, with no size-based pricing changes.","date":"2026-09-30","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/ideogram/v4.5","publisher":"fal.ai"},{"title":"pixelcut/looping-video, details and endpoints","summary":"Fal.ai released pixelcut/looping-video, a model that converts a single product image into a 5–15 second looping video with locked camera, ambient motion, or 360° spin. Pricing ranges from $0.08 to $0.32 per second depending on resolution (480p to 1080p).","date":"2026-09-30","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/pixelcut/looping-video","publisher":"fal.ai"},{"title":"veed/clean-audio, details and endpoints","summary":"Fal introduced veed/clean-audio, a model that converts noisy speech recordings into studio-quality audio. The service charges $0.0125 per input minute, rounded to the nearest minute with a 1-minute minimum. Users can upload files via drag-and-drop, URL, or clipboard, supporting formats like mp3, ogg, wav, m4a, and aac.","date":"2026-09-30","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/veed/clean-audio","publisher":"fal.ai"},{"title":"minimax/h3-max/insert-video, details and endpoints","summary":"Fal introduced a new H3 Max feature allowing users to insert AI-generated scenes into existing videos by specifying edit points and providing prompts, reference images, or videos. The feature bills at $0.05–$0.06 per second for the generated segment (480p–768p) and includes 4,096 free reference tokens, with additional tokens costing $0.02 per 1,000.","date":"2026-09-29","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/minimax/h3-max/insert-video","publisher":"fal.ai"},{"title":"google/gemini-3.8-flash-tts, details and endpoints","summary":"Fal introduced Google’s Gemini 3.8 Flash TTS, enabling expressive speech generation with 30 voices, style instructions, and support for single-speaker narration or two-speaker dialogue. The model costs $0.045 per 1,000 characters.","date":"2026-09-25","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/google/gemini-3.8-flash-tts","publisher":"fal.ai"},{"title":"google/gemini-3.8-flash-lite-tts, details and endpoints","summary":"Fal.ai introduced Google’s Gemini 3.8 Flash Lite TTS model, enabling expressive speech generation with 30 voice options and style instructions for single-speaker narration or two-speaker dialogue. The model costs $0.03 per 1,000 characters.","date":"2026-09-25","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/google/gemini-3.8-flash-lite-tts","publisher":"fal.ai"},{"title":"bytedance/seedance-2.5/draft/complete, details and endpoints","summary":"Fal introduced a new draft completion endpoint for ByteDance’s Seedance 2.5 model, enabling users to regenerate video tasks at 1080p resolution by submitting a draft ID. The endpoint costs $0.0214 per 1000 tokens and supports commercial use.","date":"2026-09-25","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/bytedance/seedance-2.5/draft/complete","publisher":"fal.ai"},{"title":"fal-ai/flux-3-action/so101","summary":"Fal introduced the Flux-3-Action SO101 model, a new endpoint designed for robotics control tasks. The model charges $0.003 per compute second, with typical calls costing $0.0015–$0.006 per invocation, equivalent to about 1 second of robot motion.","date":"2026-09-24","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/fal-ai/flux-3-action/so101","publisher":"fal.ai"},{"title":"minimax/h3-max/extend-video","summary":"Fal.ai’s minimax/h3-max/extend-video model now supports extended video generation with tiered pricing: $0.05/s at 480p, $0.08/s at 768p, $0.16/s at 1080p, and $0.32/s at 2K. Each request includes 4,096 free reference tokens, with additional tokens costing $0.02 per 1,000.","date":"2026-09-24","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/minimax/h3-max/extend-video","publisher":"fal.ai"},{"title":"minimax/h3-max/3d-to-video","summary":"Fal introduced a new 3D-to-video generation model, minimax/h3-max/3d-to-video, enabling users to convert 3D inputs into video. The model charges $0.75–$1.30 for the first 5 seconds (480p–1080p) and $0.05–$0.16 per additional second, with input costs of $0.02 per 1,000 tokens for videos/images and $0.10 per generated reference image.","date":"2026-09-24","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/minimax/h3-max/3d-to-video","publisher":"fal.ai"},{"title":"recraft/v4.1/flash/text-to-image","summary":"Fal.ai introduced recraft/v4.1/flash, a new text-to-image model generating high-quality raster images from prompts with controls for size, color, and background. The model supports commercial use and is priced at $0.007 per image, with 100 images costing $0.70.","date":"2026-09-23","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/recraft/v4.1/flash/text-to-image","publisher":"fal.ai"},{"title":"bytedance/seedream/v5/flash/edit","summary":"Fal.ai introduced bytedance/seedream/v5/flash/edit, a new image editing model optimized for speed and cost efficiency. The model supports commercial use and charges $0.027 per image, targeting workflows where budget and performance matter.","date":"2026-09-23","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/bytedance/seedream/v5/flash/edit","publisher":"fal.ai"},{"title":"fal-ai/elevenlabs/tts/multilingual-v2","summary":"Fal now offers ElevenLabs TTS Multilingual v2, enabling multilingual text-to-speech audio generation through its platform. The model supports commercial use, streaming, and API integration, with a cost of $0.1 per 1000 characters for inference.","date":"2026-09-23","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/elevenlabs/tts/multilingual-v2","publisher":"fal.ai"},{"title":"fal-ai/ace-step/prompt-to-audio","summary":"Fal introduced ACE-Step, a new model enabling text-to-audio generation from simple prompts, such as creating lofi hiphop music. The feature is available via API and playground with commercial use permitted, costing $0.0002 per second of generated audio.","date":"2026-09-23","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/fal-ai/ace-step/prompt-to-audio","publisher":"fal.ai"},{"title":"fal-ai/meshy/v6-preview/image-to-3d","summary":"Fal introduced Meshy-6-Preview, a new AI model generating production-ready 3D assets from images. The feature is available via Fal’s API for $0.8 per generation, supporting commercial use and multiple 3D formats (GLB, USDZ, FBX, OBJ).","date":"2026-09-23","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/fal-ai/meshy/v6-preview/image-to-3d","publisher":"fal.ai"},{"title":"fal-ai/kling-video/v2.5-turbo/standard/image-to-video","summary":"Fal introduced Kling Video v2.5-turbo, an upgraded image-to-video model with enhanced input flexibility (drag-and-drop, URLs, clipboard) and broader file type support. The new model charges $0.21 for 5 seconds and $0.042 per additional second.","date":"2026-09-22","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/standard/image-to-video","publisher":"fal.ai"},{"title":"fal-ai/kling-video/v3/turbo/pro/image-to-video","summary":"Fal introduced the Kling Video v3 Turbo Pro image-to-video model, enabling users to generate video from images. The service charges $0.14 per second of video output, with a 5-second video costing $0.70.","date":"2026-09-22","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/image-to-video","publisher":"fal.ai"},{"title":"tripo3d/p2/text-to-3d","summary":"Fal introduced explicit pricing tiers for its tripo3d/p2 text-to-3D model, ranging from $1.00 per model without textures to $1.30 with extreme textures. PBR textures and quad topology are available at incremental costs, with examples provided for standard texture batches.","date":"2026-09-22","dateIsEstimated":true,"signalType":null,"signalTypeLabel":null,"sourceUrl":"https://fal.ai/models/tripo3d/p2/text-to-3d","publisher":"fal.ai"},{"title":"tripo3d/p2/image-to-3d","summary":"Fal.ai launched tripo3d/p2, an image-to-3D model generation feature with transparent per-model pricing. Costs range from $1.00 per model without textures to $1.30 with extreme textures, with PBR and texture options adding incremental fees. Quad topology incurs no extra charge.","date":"2026-09-22","dateIsEstimated":true,"signalType":"pricing_update","signalTypeLabel":"Pricing","sourceUrl":"https://fal.ai/models/tripo3d/p2/image-to-3d","publisher":"fal.ai"},{"title":"pixverse/music-video/vibemv","summary":"Fal introduced VibeMV, an AI model generating music videos from audio inputs, priced at $0.06/second for 720p and $0.09/second for 1080p. The tool accepts MP3, OGG, WAV, M4A, or AAC files and enforces a 10-second minimum and 6-minute maximum per request.","date":"2026-09-22","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/pixverse/music-video/vibemv","publisher":"fal.ai"},{"title":"minimax/h3-max/styles/retro-toon-70s","summary":"Fal introduced a new 'Retro Toon 70s' style for its H3 Max Director model, generating 768p videos with audio in a hand-painted 1970s animation aesthetic. The style supports 5–15 second durations and costs $0.08 per second, with a 5-second video priced at $0.40 and a 15-second video at $1.20.","date":"2026-09-21","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/minimax/h3-max/styles/retro-toon-70s","publisher":"fal.ai"},{"title":"minimax/h3-max/styles/low-poly","summary":"Fal introduced a new low-poly 3D style for its H3 Max video generation model, producing 768p videos with audio from text prompts or images. Pricing is $0.08 per second, with 5-second videos costing $0.40 and 15-second videos $1.20.","date":"2026-09-21","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/minimax/h3-max/styles/low-poly","publisher":"fal.ai"},{"title":"minimax/h3-max/styles/hand-drawn","summary":"Fal.ai expanded its H3 Max video generation model with a new 'hand-drawn' animation style, producing 768p videos with audio from text prompts or first-frame images. Pricing is $0.08 per second, with 5-second videos costing $0.40 and 15-second videos $1.20.","date":"2026-09-21","dateIsEstimated":true,"signalType":"feature_update","signalTypeLabel":"Feature","sourceUrl":"https://fal.ai/models/minimax/h3-max/styles/hand-drawn","publisher":"fal.ai"},{"title":"minimax/h3-max/styles/16bit-pixel","summary":"Fal introduced the H3 Max Director model, enabling 768p video generation with audio in a 16-bit pixel-art style from text prompts or first-frame images. Videos range from 5–15 seconds, priced at $0.08 per second ($0.40 for 5s, $1.20 for 15s).","date":"2026-09-21","dateIsEstimated":true,"signalType":"product_launch","signalTypeLabel":"Launch","sourceUrl":"https://fal.ai/models/minimax/h3-max/styles/16bit-pixel","publisher":"fal.ai"}],"attribution":{"source":"Spyingbee","url":"https://spyingbee.com/updates/fal","citation":"Spyingbee, \"Fal updates\", https://spyingbee.com/updates/fal (retrieved 2026-10-08)"}}