GLM Flash Latest

This alias currently points to GLM 5.3 Flash. AnonRouter updates it after reviewing a newer stable model in the same family. Each request is pinned to one concrete model; prices, limits, and provider availability can change when the alias is updated. Use the concrete model ID to stay on a fixed version.

Listed input rates are $0.075–$0.15; output rates are $0.35–$0.50, per million tokens. Rates and cache discounts vary by provider. Check the Providers section for the route you choose.

The model catalog lists a context window of 1,048,576 tokens and up to 16,384 output tokens. Individual providers can have lower limits; check their rows in the Providers section.

Yes. The catalog lists these modalities: text, image, video. Available inputs and outputs depend on the serving route.

Tool calling is advertised for this model. Reasoning is also advertised; available controls vary by provider.

Currently callable routes offer these privacy levels: Private, Anonymous. Privacy depends on the provider route. Check the privacy badge and route details before choosing a provider; the Privacy section explains the strongest available level.

Open it in Chat, or use the Quickstart button above for an API example with this model's ID, ~z-ai/glm-flash-latest. Available interfaces depend on the model's modality and provider.