Qwen-Audio-3.1-Realtime-Plus
Qwen-Audio-3.1-Realtime-Plus is a real-time, full-duplex speech conversation model. It accepts text and audio and can return text and audio. It supports function calling, web search and voice cloning;…
MODEL DIRECTORY
New releases, in one place. Explore models by their publication date.
Qwen-Audio-3.1-Realtime-Plus is a real-time, full-duplex speech conversation model. It accepts text and audio and can return text and audio. It supports function calling, web search and voice cloning;…
Qwen-Image-2.1 is a unified text-to-image generation and image-editing model with downloadable weights. Its visual generation component has 7 billion parameters and 32 single-stream DiT layers. It was…
Qwen3.8-LiveTranslate is a multilingual real-time audio and video interpretation model. The specified API model accepts audio and images and can return translated text and synthesized speech. The…
HappyOyster Acting is a real-time interactive role-play model in Alibaba Cloud Model Studio. It uses text and images to generate characters and scenes in a specified persona style; subsequent text…
HappyOyster Directing is a real-time interactive, immersive open-world model served through Alibaba Cloud Model Studio. Alibaba lists happyoyster-1.0-directing as released on September 17, 2026. (help…
HappyOyster Adventure is a real-time, interactive open-world model served through Alibaba Cloud Model Studio. The official model release list dates it to September 17, 2026; a separate product…
Qwen3.8-Omni-Flash is a native multimodal model for audio and video understanding, content analysis, and agent applications. It accepts text, images, audio, and video and produces text. Alibaba Cloud…
Baidu Flex is an end-to-end speech-language model for flexible, task-oriented real-time voice interactions. Its public beta was announced on September 16, 2026. (cloud.baidu.com) Understands speech…
Google announced Gemini 3.8 Live Extended Thinking on September 15, 2026; the announcement was updated on September 17, 2026. It is a real-time, audio-to-audio Live API model designed for complex,…
Gemini 3.8 Live is a low-latency, audio-to-audio model for real-time dialogue and voice agents. Google positions it for scalable, cost-efficient conversational applications with visual grounding. It…
K2.8 Preview is a preview coding and agent model offered through Kimi Code. It was fully rolled out on September 11, 2026, under the existing kimi-for-coding model ID. Moonshot describes its overall…
Released on September 10, 2026, DeepSeek-V4.1-Flash is an efficiency-oriented, multimodal model with native visual understanding. It uses a 552-billion-parameter mixture-of-experts architecture with…
AuK-Flash is the distilled, four-step inference variant of AuK, Tencent’s 1.5-billion-parameter foundation model for speech generation and editing. It accepts natural-language instructions and,…
AuK is an open-source, 1.5-billion-parameter foundation model for speech generation and editing through natural-language instructions and, where needed, reference audio. This entry describes the base…
GPT-Image-2.5 Sunburst is OpenAI’s image generation and editing model for visual workflows that require precise, controlled edits. OpenAI announced it on September 8, 2026. Its dated API snapshot is…
GPT-Image-2.5 Flare is OpenAI’s speed-oriented image generation and editing model for everyday applications. OpenAI announced it on September 8, 2026. The dated API snapshot is gpt-image-2.5-flare-202…
Qwen-Drive-1.0 is a vision-language foundation model for autonomous-driving research. It builds on the multimodal Qwen3.5-4B backbone and combines 3D perception, visual question answering and motion…
GPT-6 Astra is OpenAI’s model for demanding end-to-end work. OpenAI lists complex reasoning, coding, computer use, research, and document creation among its intended uses. It can assist with multistep…
WeatherNext 3 is a global probabilistic AI weather-forecasting model developed by Google DeepMind and Google Research. It is not a general-purpose language model. It uses a Functional Generative…
Gemini 3.8 Flash Cyber is a post-trained version of Gemini 3.8 Flash designed for cybersecurity. Google positions it for trusted defenders, with a particular emphasis on autonomous vulnerability…