---
name: Glm-5V-Turbo
slug: glm-5v
type: Multimodal
providers:
  - zai
  - 302ai
  - nano-gpt
  - zhipuai-coding-plan
  - venice
  - vercel
  - zenmux
  - zhipuai
  - openrouter
description: 'GLM vision model for visual reasoning, documents, and multimodal agents'
tags:
  - reasoning
  - tool-use
  - multimodal
  - glm
is_open_source: false
context_window: 202800
max_output: 131072
pricing:
  - image: 0
    input: 0.72
    output: 3.2
    provider: 302ai
  - image: 0
    input: 1.2
    output: 4
    provider: nano-gpt
  - image: 0
    input: 1.5
    output: 5
    provider: venice
  - image: 0
    input: 1.2
    output: 4
    provider: vercel
  - image: 0
    input: 1.2
    output: 4
    provider: zai
  - image: 0
    input: 0.726
    output: 3.1946
    provider: zenmux
  - image: 0
    input: 0
    output: 0
    provider: zhipuai-coding-plan
  - image: 0
    input: 5
    output: 22
    provider: zhipuai
  - image: 0
    input: 1.2
    output: 4
    provider: openrouter
release_date: '2026-04-02'
openrouter_id: z-ai/glm-5v-turbo
capabilities:
  audio: true
  vision: true
  tool_use: true
  citations: false
  reasoning: true
---
Glm-5V-Turbo is a Multimodal model.
GLM vision model for visual reasoning, documents, and multimodal agents