MODEL DIRECTORY

Latest AI models

New releases, in one place. Explore models by their publication date.

Newest first7 languages
Clear

345 models

Newest first
MiniMax

VTP-Small-f16d64

VTP-Small-f16d64 is the Small checkpoint in the VTP visual-tokenizer research project involving MiniMax and Huazhong University of Science and Technology. It is intended for image feature extraction…

Alibaba

Qwen-Image-Edit-Plus

Qwen-Image-Edit-Plus is an image-editing model. This version is the December 15, 2025 snapshot and was listed in Alibaba’s release announcement on that date. It takes images and editing instructions…

Alibaba

Wan2.6-Image

Wan2.6-Image is an all-round image generation and editing model available through Alibaba Cloud Model Studio. Alibaba’s release log lists it under December 15, 2025 for the Global deployment scope.…

Alibaba

Wan2.6-T2I

Wan2.6-T2I is Alibaba’s text-to-image model, served through Alibaba Cloud Model Studio. The official release log lists it on December 15, 2025. Alibaba describes improvements in visual quality,…

Alibaba

Qwen Voice-Design

Qwen Voice-Design is a Qwen speech-model service for creating a custom voice from a short text description. Used with qwen3-tts-vd-realtime, it can generate speech in 10 languages; the resulting…

Google

Gemini 2.5 Flash Native Audio Preview

A preview native-audio model for the Gemini Live API, designed for low-latency, real-time voice and video interaction. Google says the December 2025 update improves handling of complex workflows. It…

Zhipu AI

GLM-TTS

GLM-TTS is a text-to-speech system for generating expressive speech from text. Zhipu AI announced it on December 10, 2025, and released model weights for local deployment. (zhipuai.cn) Supports…

Zhipu AI

GLM-ASR-Nano-2512

GLM-ASR-Nano-2512 is an open-source automatic speech recognition model designed to transcribe speech in complex real-world conditions. It takes audio as input and produces text. The official…

Alibaba

Qwen3-LiveTranslate-Flash

Qwen3-LiveTranslate-Flash is a multilingual audio and video translation model built on Qwen3-Omni infrastructure. It supports offline and real-time translation, using visual context to help interpret…

Alibaba

Qwen3-Omni-Flash

Qwen3-Omni-Flash is an omni-modal model based on a Thinker–Talker mixture-of-experts architecture. The dated version was listed as released on December 4, 2025. It accepts text, images, audio and…

Alibaba

Qwen3-Omni-Flash-Realtime

Released on December 4, 2025, this is the real-time version of Qwen3-Omni-Flash, a multimodal model based on a Thinker–Talker mixture-of-experts architecture. The dated model ID identifies the…

Alibaba

Wan2.6-I2V

Wan2.6-I2V is Alibaba’s image-to-video generation model, available through Alibaba Cloud Model Studio. It uses an input image as the first frame and can also take a text prompt and optional audio. It…

Alibaba

Wan2.6-T2V

Wan2.6-T2V is Alibaba’s text-to-video generation model, available through Alibaba Cloud Model Studio. It supports text and audio inputs and generates video with audio. Its intelligent shot scheduling…

Alibaba

Qwen-Plus

Qwen-Plus is a text-generation and reasoning model offered through Alibaba Cloud Model Studio. This ID identifies the snapshot released on December 1, 2025. Alibaba reports improved reasoning, agent…

DeepSeek

DeepSeek-V3.2-Speciale

Released on December 1, 2025, DeepSeek-V3.2-Speciale is an open-weight, high-compute variant of DeepSeek-V3.2 designed for deep reasoning and research. It combines extended thinking with…

DeepSeek

DeepSeek-V3.2

DeepSeek-V3.2 is a general-purpose, reasoning-oriented language model designed to balance reasoning ability and output length for everyday questions and agent tasks. It was released on December 1, 202…

Alibaba

Qwen-Voice-Enrollment

Qwen-Voice-Enrollment is a Qwen voice-cloning model for creating a reusable voice from a reference recording. Alibaba lists it under November 27, 2025 in its official model release announcement. (help…

DeepSeek

DeepSeekMath-V2

DeepSeekMath-V2 is a mathematical reasoning model optimized for natural-language theorem proving. It is built on DeepSeek-V3.2-Exp-Base and can generate, assess and iteratively refine proofs. Its…

Alibaba

Qwen3-TTS-Flash

Qwen3-TTS-Flash is Tongyi's non-real-time text-to-speech model: it takes text as input and produces audio. This ID identifies the 2025-11-27 snapshot. Alibaba's release listing places it under…

Alibaba

Qwen3-TTS-Flash-Realtime

Qwen3-TTS-Flash-Realtime is a real-time text-to-speech model served through Alibaba Cloud Model Studio. It takes text as input and produces audio, targeting low-latency speech synthesis. It supports…