GLM-5.2 gains vision support on Baseten, enabling image-to-code

baseten · x · 2026-08-22

GLM-5.2 now supports vision capabilities on Baseten, allowing users to ingest images and convert them into code. Developed by Z.AI, this next-gen model is designed for agentic engineering with enhanced coding and agentic capabilities for long-horizon tasks. It features a MoE + DSA architecture and is priced at $1.40/1M input tokens and $4.40/1M output tokens.

Original post →

More from coding & agent

coding & agent channel →