GLM 5.3 Flash NVFP4
Quantization of Z.ai's GLM-5.3-Flash model in NVFP4 precision, the first natively multimodal model in the GLM-5 series: a 320-billion-parameter Mixture-of-Experts model with 18B active parameters per token and a one-million-token context window, built for coding and agentic work.
Model
GLM-5.3-Flash pairs sparse attention with linear attention in a hybrid architecture that reduces attention computation and KV-cache size. Trained on a multimodal corpus, it integrates visual understanding directly into coding and agentic workflows. Full details are in Z.ai's announcement.
Shared Endpoint
On a Shared Endpoint, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.