---
name: Glm 4.6V Original
slug: glm-4-6v-original
type: Multimodal
providers:
  - nano-gpt
description: 'GLM vision model for visual reasoning, documents, and multimodal agents'
tags:
  - open-source
  - multimodal
  - glm
is_open_source: true
context_window: 128000
max_output: 24000
pricing:
  - image: 0
    input: 0.6
    output: 0.9
    provider: nano-gpt
release_date: '2025-12-08'
capabilities:
  audio: false
  vision: true
  tool_use: false
  citations: false
  reasoning: false
---
Glm 4.6V Original is a Multimodal model.
GLM vision model for visual reasoning, documents, and multimodal agents