GLM-5V-Turbo

Name: GLM-5V-Turbo
Author: Zhipu AI

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

Live

Open / InstallLast updated August 5, 2026

Description

Fast GLM vision model for screenshots, documents, and multimodal agent tasks. Supports a context window of 200,000 tokens. Supports extended reasoning. Supports tool calling. Input priced at $5 per million tokens. Weights are not publicly released; access is via the provider API.

Author

Zhipu AI

Platform

api

Pricing model

paid

Capabilities

Text generation
200,000 token context
Extended reasoning
Tool calling
File attachments
Image input

Benchmarks

No benchmark results have been added yet.