Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Mini Program Growth Plan adds DeepSeek-v4.1-flash and Hy4 Preview to token allowance

AI summary

According to 掘金·人工智能, the AI resource package included in WeChat's Mini Program Growth Plan now supports two newly added deductible models, hy4-preview and deepseek-v4.1-flash, bringing the 1-billion-token text-generation allowance to three supported text models including hy3. The report says none of the three need to be enabled in the cloud-development console, and token usage from mini-program clients, the cloud-development server or the console is deducted automatically from the gifted allowance without extra configuration. It also notes that the Hy-image-v3.5-preview image model and the newly released Hy4 are still being integrated, with a separate notice to follow.

In-depth insight

The update lets mini-program developers call DeepSeek-v4.1-flash and Hy4 Preview inside the free 1-billion-token allowance without switching models on in the console, which directly lowers setup friction for image recognition and long-document workloads.

小程序成长计划赠送的 AI 资源包,今天新增两个可抵扣模型:hy4-preview、deepseek-v4.1-flash。加上原有的 hy3,10 亿 Token 生文额度现在共支持三个文本模型。

这次上新后,三个模型都不需要在云开发控制台开启。在小程序端、云开发服务端或云开发控制台调用时,Token 用量自动从赠送额度扣除,无需额外配置。

▍怎么应用到你的小程序中

你可以直接对照下表,把新能力代入你的业务:

推荐业务场景改哪里
拍图识别(拍发票一键报销、扫试卷自动批改、商品截图自动分类、识图提取表格)替换 model 为 "deepseek-v4.1-flash",直接传入图片云存储 URL。
长文本处理(批量解析长文档、客服聊天记录长文本归纳总结、智能助理多轮长对话)替换 model 为 "hy4-preview",无需再做繁琐的上下文裁切和截断逻辑。

生图模型 Hy-image-v3.5-preview 与刚刚发布的正式Hy4也已在接入中,上线后另行通知。

▍怎么领取

#DeepSeek-v4.1-flash#Hy4 Preview#Hy-image-v3.5-preview#hy3#Tencent Cloud Development#WeChat Mini Program

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.