> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# glm-5-3-flash-260828 Is Live: GLM-5.3-Flash via BytePlus

> New model glm-5-3-flash-260828 is GLM-5.3-Flash served through BytePlus (ByteDance's international cloud) as an official relay, available in the default / svip / CodexResponses groups. Priced the same as glm-5.3-flash: $0.15 input / $0.50 output / $0.03 cache read per 1M tokens, with text, image and video input and deep thinking.

**2026/9/19 00:46 (UTC+8)** · New Model · Zhipu / ByteDance

🚀 **`glm-5-3-flash-260828` is live in the `default` / `svip` / `CodexResponses` groups**

This is Zhipu's GLM-5.3-Flash served through **BytePlus (ByteDance's international cloud) as an official relay**; `260828` is the BytePlus version snapshot. GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series, taking text, image and video input and producing text, with deep thinking.

Pricing matches `glm-5.3-flash`, launched on 9/8: \$0.15 input / \$0.50 output / \$0.03 cache read per 1M tokens, and recharge bonuses apply as usual. GLM-5.3-Flash is now available under two model names; pick either:

* `glm-5.3-flash`: official relay via Zhipu
* `glm-5-3-flash-260828`: official relay via BytePlus

📖 Benchmarks, specs and code samples: [GLM-5.3 and GLM-5.3-Flash Launch](/en/news/glm-5-3-launch) · [GLM-5.3-Flash model details](/en/models/glm-5-3-flash)

***

← [Back to Live Updates](/en/live) · 📚 [Monthly archive](/en/live/archive)