Runtime, the conference for engineers running AI in production. Oct. 1 in SF Register now

GLM 5.3 Flash

GLM-5.3-Flash is the first natively multimodal model in Z.ai's 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.

Related resources

Ship your first app in minutes.

Get Started

$30 / month free compute