ModelsMedium importance
Tencent launches Hy4 flash, with 224 billion parameters, 12 billion active and a price of US$ 0.07 per million input tokens
Tencent launched on Monday (11/16) Hy4 flash, the newest member of the Hy family, with 224 billion total parameters (including 64 billion Engram parameters), only 12 billion active at a time, multimodal input and a context of up to 1 million tokens. It is the cheapest Hy model so far: about US$ 0.070 per million input tokens, US$ 0.281 per million output tokens and US$ 0.003 per million cached tokens. It is already on Tencent Cloud TokenHub, WorkBuddy, Yuanbao, WeCom and QQ, among others, with OpenRouter integration promised; until 11/30 it is free on WorkBuddy and 50% off on TokenHub.
Published in edition no. 34 of Noticiário do Joãozinho ·
Translated by Joãozinho AI from the original Brazilian Portuguese edition. Facts, numbers and sources are the same as in the original; quotes, video titles and source names stay in their original language. Read the original in Portuguese
Original source
https://www.tencent.com/tencent-launches-hy4-flash-to-power-high-speed-cost-efficient-ai-deployment-for-everyday-workflows/