Cloudflare announced the addition of Z.ai's GLM-5.3 Flash to its Workers AI platform. The model is now available under the identifier @cf/zai-org/glm-5.3-flash.
The GLM-5.3 Flash is built on a Mixture-of-Experts architecture, featuring 320B total parameters with 18B active per token. It is the first model in the GLM-5 series to support native multimodal inputs on Workers AI.
According to the vendor, GLM-5.3 Flash outperforms the previous GLM-5.2 iteration across benchmarks and real-world workloads at a lower price point. The vendor claims it approaches Claude Opus 4.8 on coding and agentic benchmarks.
Access to GLM-5.3 Flash requires a Workers Paid plan or prepaid AI Gateway credits. Developers can invoke the model using the Workers AI binding (env.AI.run()), the REST API, the OpenAI-compatible endpoint, or via AI Gateway.