Models

4,400 in the directory.

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17

Most downloaded A–Z Recently synced

Voyage large 2 instruct Voyage AI voyage-large-2-instruct is a general-purpose text embedding model with a 16K context window and 102… Text · Closed Closed weights
Voyage law 2 Voyage AI Text embedding model optimized for legal retrieval and RAG. Trained on 1 trillion legal tokens with… Text · Closed Closed weights
Voyage lite 01 Voyage AI Lightweight text embedding model from Voyage AI for retrieval-augmented generation and semantic sea… Text · Closed Closed weights
Voyage lite 01 instruct Voyage AI Lightweight text embedding model fine-tuned on top of voyage-lite-01 for classification and cluster… Text · Closed Closed weights
voyage lite 02 instruct Voyage AI voyage-lite-02-instruct is a lightweight instruction-tuned text embedding model from Voyage AI's se… Text · Closed Closed weights
Voyage multilingual 2 Voyage AI Text embedding model optimized for multilingual retrieval and RAG. Supports 27 languages including… Text · Closed Closed weights
Voyage multimodal 3 Voyage AI Multimodal embedding model that vectorizes interleaved text and images through a unified transforme… Multimodal · Closed Closed weights
Voyage multimodal 3.5 Voyage AI Multimodal embedding model that vectorizes interleaved text, images, and videos into a shared vecto… Multimodal · Closed Closed weights
VQGAN-CLIP EleutherAI AI model by EleutherAI Image · Closed Closed weights
VR-1 Cogent VR-1 is a frontier reasoning model trained specifically for cyber defense. Given a foothold inside… Text · Closed Closed weights
Waldo Glean Waldo is an agentic search model built on NVIDIA Nemotron 3 Nano that plans and executes search ste… Text · Open weights Open weights
Wan 2.2 A14B Alibaba Text and image to video model focused on stable motion and clear detail with practical latency. Video · Closed Closed weights
Wan 2.5 Alibaba Wan 2.5 is the next-gen text-to-video system. It delivers sharper detail, longer and more stable sh… Video · Closed Closed weights
Wan 2.5 Preview Alibaba Preview build that showcases higher fidelity, better physics, and longer shot stability. Video · Closed Closed weights
Wan 2.6 Alibaba Wan 2.6 is Alibaba’s latest Wan AI multimodal video model, turning text, images, audio and short re… Multimodal · Closed Closed weights
Wan 2.7 Alibaba Wan 2.7 appears to be the latest generation of the Wan AI creative model line, focused on image and… Multimodal · Closed Closed weights
Wan 3 Alibaba Wan 3 is Alibaba's multimodal video generation model that creates up to 30 seconds of video in a si… Video · Open weights Open weights
Wan Streamer v0.2 Alibaba Wan-Streamer v0.2 is an end-to-end Transformer model for real-time duplex audio-visual conversation… Multimodal · Closed Closed weights
Wan2.7 Image Alibaba Wan2.7-Image is Alibaba’s image generation and editing model family for high-volume, highly control… Image · Open weights Open weights
Wan2.7 Video Alibaba Wan2.7-Video is Alibaba’s comprehensive video generation suite for director-style creation and edit… Multimodal · Open weights Open weights
WaveNet Google DeepMind WaveNet is DeepMind’s generative raw-audio model for speech synthesis and audio waveform generation. Audio · Closed Closed weights
WavFlow Meta Platforms WavFlow is Meta AI’s open-source audio-generation model for creating synchronized high-fidelity aud… Multimodal · Closed Closed weights
Waymo World Model Waymo Generative world model used to simulate diverse driving scenarios for autonomous vehicle training,… Multimodal · Open weights Open weights
WeatherNext 2 Google WeatherNext 2 is Google DeepMind and Google Research’s latest AI weather forecasting model family f… Text · Closed Closed weights
WeatherNext 3 Google WeatherNext 3 is Google DeepMind and Google Research's next-generation AI weather forecasting model… Text · Closed Closed weights
Wholembed v3 mixedbread ai Wholembed v3 is Mixedbread’s unified omnimodal, multilingual late-interaction retrieval model built… Multimodal · Open weights Open weights
WildDet3D Ai2 WildDet3D is Ai2’s open model for monocular 3D object detection from a single RGB image. It predict… 3D · Open weights Open weights
Willow Frontier Mini Willow Willow's free, unlimited speech to text model powering the Basic tier of the Willow dictation app o… Audio · Closed Closed weights
Willow Frontier Pro Willow Willow's most accurate speech to text model, built for power users and teams on the paid Individual… Audio · Closed Closed weights
Windsurf 2.0 Cognition Windsurf 2.0 is Cognition’s upgraded agentic coding workspace centered on local and cloud agents wo… Text · Closed Closed weights
WuDao 2.0 Beijing Academy of Artificial Intelligence (BAAI) AI model by Beijing Academy of Artificial Intelligence (BAAI) Text · Open weights Open weights
Xiaomi MiMo V2 Omni Xiaomi MiMo-V2-Omni is an omni foundation model that unifies multimodal understanding with agentic capabil… Multimodal · Closed Closed weights
Xiaomi MiMo V2 Pro Xiaomi MiMo-V2-Pro is Xiaomi’s flagship foundation model built for real-world agent workloads, designed to… Text · Closed Closed weights
Xiaomi MiMo V2 TTS Xiaomi MiMo-V2-TTS is Xiaomi’s large-scale speech synthesis model built for expressive agent voice, aiming… Audio · Closed Closed weights
XMAX X1 Xmax AI XMAX X1 is a real-time interactive video model that fuses virtual and real worlds, using the phone… Video · Open weights Open weights
YaLM Yandex AI model by Yandex Text · Closed Closed weights