Tavory wird geöffnet
Loading Tavory
Tavory wird geöffnet
Loading Tavory
Provider directory
Compare 6 distinct Tencent models represented in Tavory across video generation, text and chat. Regional duplicates are consolidated into canonical model pages.
Tavory is an independent AI workspace and does not represent a manufacturer relationship unless explicitly stated. Model ownership and trademarks remain with their respective providers.
Distinct models
6
Categories
video, text
Catalog policy
Regional duplicates consolidated
Tencent
GLM-5.3-FlashX is the enhanced, high-speed (~200 tokens/s) variant of GLM-5.3-Flash with a 1M token context window and image, video and file understanding.
Tencent
Hy3 is Tencent's open-weight (Apache 2.0) MoE model with a 256K context window, optimized for agentic workflows, coding and productivity tasks with strong token efficiency.
Tencent
Hy4 preview is Tencent's flagship class MoE model with 770B total parameters and 49B activated, supporting a 1M token context window. It is optimized for agent, coding, and productivity scenarios, with strong task decomposition, context tracking, instruction following, and long chain execution. It is suited for coding agents, complex tool use, and multi step agentic workflows.
Tencent
Kimi's most intelligent coding model to date. It follows instructions more reliably across long contexts and achieves higher success rates on coding tasks. Supports text, image, and video inputs, as well as reasoning, chat, and agent workflows.
Tencent
Kimi K2.7 Code HighSpeed is the higher-throughput variant of Kimi K2.7 Code, Moonshot's coding model with a 256K context window that follows instructions reliably across long agentic sessions.
Tencent
MiniMax-M3 is MiniMax's latest model, achieving frontier capabilities in professional tasks such as programming and agents. It uses the new attention architecture MSA (MiniMax Sparse Attention), supports up to 1M ultra-long context, and is a native multimodal model supporting image and video input.
Choose an eligible model from the catalog or let Smart Mode select a suitable available route. Tavory checks capabilities, plan access and current availability server-side when a request is sent.
