GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cantina-security
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
cantina-security
Model Tree
cantina-security/apex-flash-1
Input Modalities
Output Modalities
Supported Functionality
This variant has not undergone a separate full-suite evaluation. The results reported for apex-flash-1 apply to the standard checkpoint and should not be attributed to this derivative. Changes in refusal behavior do not establish improvements in security-task performance or reliability.
The checkpoint retains the standard model's image-text-to-text architecture. Image and video performance have not been evaluated for this variant.
The checkpoint uses the GLM-5.3-Flash architecture and is distributed in BF16. See the standard model card for the training overview and intended worker-model use.
Explore Apex to learn more about Cantina's security research system.
Read the Apex Flash release post for the training methodology and case examples.