F24 SALES / MODEL
dealignai
GLM 5.3 Flash Uncensored FP8
Dealignai's GLM 5.3 Flash derivative is intended for alignment research and conversational generation with reduced refusals. It modifies model weights directly and publishes an FP8 checkpoint whose creator documents vision, tool calling and speculative decoding support.
Free aggregator routes
These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.
Limits above: GMI Cloud. Available gateway routes are listed below.
The supplied GMI catalog identifies the exact namespaced repository published by dealignai. Its model card explicitly credits dealignai for the weight modification and release; Z.ai created the underlying GLM-5.3-Flash model. This derivative remains distinct from standard GLM-5.3-Flash. GMI does not identify a pinned repository revision.
GMI Cloud
Info- Thinking
- Not documented
dealignai/GLM-5.3-Flash-UNCENSORED-FP8Model sources
Use it through LiteLLM
Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.
Download LiteLLM YAML