Wispr Flow - Don’t type, just speak
Mini toolsGLM 4.6V
By Z.ai
Model family: GLM
GLM-4.6V is a multimodal large language model series built for real-world agentic workflows. It ships in two sizes: GLM-4.6V (106B) for cloud and high-performance environments, and GLM-4.6V-Flash (9B) for local and low-latency deployment. A core feature is native multimodal tool calling, enabling images, screenshots, and documents to be passed directly as tool parameters without text conversion, and allowing visual results from tools to feed back into the model's reasoning chain. The 128K context window handles roughly 150 complex document pages, 200 slide pages, or a one-hour video in a single pass. Key use cases include rich-text content creation from multimodal sources, visual web search with structured output, and pixel-level frontend replication from screenshots with iterative visual feedback. The model employs a Visual Feedback Loop for self-correction, inspecting rendered output and refining code or actions autonomously.
Multimodal
Gen 3
Overview
Open-source multimodal model series with native function calling. Available in 106B (cloud) and 9B Flash (local) variants. Features a 128K context window, supports image and video understanding, and can perform agentic tasks combining visual perception with direct tool execution, including web search and document-to-article generation.
About Z.ai
Z.ai (formerly Zhipu AI) is a Chinese AI company developing large language models (GLM series), combining reasoning, coding, and agent capabilities, and offering open models and APIs.
Industry:
Artificial Intelligence
Company Size:
800
Location:
Beijing, Beijing, CN
Website:
chat.z.ai
Last updated: June 22, 2026
