GLM-5.3 live on Phala inside TDX-attested GPU TEE, 1M context at $1.40/M input

bgmshana · x · 2026-09-01

Phala Network announced that Z.ai's GLM-5.3 is now served on its platform inside a TDX-attested GPU TEE for private inference. The model targets complex software engineering and long-horizon agent tasks, with a 1M-token context window, tool use, and structured outputs. Pricing: $1.40/M input, $4.40/M output. Phala reports 1.2s TTFT, 56 tps throughput, and 97.81% uptime over the last 72 hours. The catalog also includes GLM-5.3 Flash (320B MoE, $0.15/M input) and other TEE-deployed models.

Original post →

More from Models

Models channel →