GLM 5.3

GLM 5.3 is Z.ai's open-weight mixture-of-experts language model with 753 billion parameters and a 1M-token context window. It uses the same base model as GLM-5.2, with post-training that makes it much better at complex coding and long-horizon tasks.

Z.ai says GLM 5.3 uses the same base model as GLM-5.2 and that every gain comes from post-training. Z.ai reports that it is much better at complex coding and long-horizon tasks.

Yes. Z.ai documents a thinking budget with three levels, low, high and max, and the model defaults to max when no level is set.

GLM 5.3's configuration supports 1,048,576 positions, and Z.ai evaluates it with a 1M-token context window. The context and output limits available on Alchemy Inference are shown in your dashboard.

GLM 5.3 is released under the GLM-5.3 License: MIT-style permissions with an additional condition for the very largest Model-as-a-Service providers. Read the full license on Hugging Face before building on the open weights.

With Token Based APIs, call GLM 5.3 through Alchemy's OpenAI-compatible API with the model ID zai-org/GLM-5.3 and pay for the tokens you use. Dedicated Deployments are not offered for this model. Join the waitlist for early access; once you're in, the in-app quickstart walks you through your first request.

Current pricing and limits for GLM 5.3 are listed in your dashboard once you're in.

Alchemy Inference operates with zero data retention (ZDR).