GLM-4.7-Flash NVFP4 — 30B MoE, 3B active, tools + reasoning, MIT
Full machine-readable API references: llms.txt (agent guide), openapi.json (OpenAPI 3.1), docs.
GLM-4.7-Flash-NVFP4-TEE
/v1/chat/completions
Run this model with your Chutes account, quota, and API access.