Parameters
MoE · FP8 · vision · 330 GBOpen Model Catalogue
Z.ai
Text generationReasoningVisionCoding
GLM-5.3 Flash
zai-org/GLM-5.3-FlashZ.ai newest — MIT, 4 × H200
Min VRAM
≈ 380 GBHardware
5 × 80 GB GPUOpenAI-compatible API with a per-workload key — drop-in for existing SDKs.
Dedicated GPUs — your model, your instance, no shared queues.
Billed by the second with auto-shutdown — never pay for idle time you didn't plan.