Wispr Flow - Don’t type, just speak
Mini toolsGLM 4.7 FlashX
By Z.ai
Model family: GLM
GLM-4.7-FlashX is the premium-tier API variant within the GLM-4.7 series, designed for developers requiring higher throughput and priority routing. It delivers competitive performance in coding, reasoning, and agentic tasks with low latency. Key capabilities include multiple thinking modes for flexible reasoning, real-time streaming, function calling for external tool integration, intelligent context caching for long conversations, and structured JSON output for system integration. The model supports a 200K context window with up to 128K maximum output tokens. It performs well across coding tasks (frontend and backend), Chinese writing, translation, long-form content processing, and role-playing. On agentic benchmarks, it achieves strong results on SWE-bench Verified and t2-Bench among models of comparable scale.
Text
Gen 7
Overview
GLM-4.7-FlashX is a lightweight, high-speed text model from Z.AI's GLM-4.7 series, optimized for high-throughput API use. It supports a 200K context window and up to 128K output tokens, with thinking mode, function calling, context caching, and structured JSON output.
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
