Zhipu's GLM-5.3-Flash Lands on CoreWeave Serverless Inference

Zhipu's GLM-5.3-Flash is now available on CoreWeave's serverless inference, also accessible via Weights & Biases, offering 1M token context and vision support at $0.5 per million output tokens. It ranks among the top five open-weight models on Artificial Analysis's index with 18B active parameters.

2026-09-09 ~ 2026-09-10 · 2 related posts

• GLM 5.3 Flash goes live on W&B serverless inference: 1M context, vision, $0.50/M output — wandb · 2026-09-09
• GLM-5.3-Flash hits CoreWeave: top-5 open model with just 18B active params — wandb · 2026-09-10