# GLM-4.5V

> Open-weight 106B/12B-active vision-language MoE with a toggleable thinking mode for images, video, documents and GUI agents.

- Maker: Z.ai (Zhipu / GLM)
- Line: GLM-V (vision-language)
- Canonical page: https://ai-tldr.dev/models/glm-4-5v/
- Updated: 2026-06-18

## In short

GLM-4.5V is the open-weight vision-language model in Z.ai's (Zhipu / GLM) GLM-V line, released on August 11, 2025. It is a Mixture-of-Experts model with 106B total parameters and 12B activated per token, built on top of the GLM-4.5-Air-Base text foundation. It has a 64K-token context window and costs $0.60 per million input tokens and $1.80 per million output tokens. You can use it through Z.ai API Platform and OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 64K (max output 16K) | [1] |
| Input price | $0.60 / 1M tokens (cached $0.11 / 1M tokens) | [2] |
| Output price | $1.80 / 1M tokens | [2] |
| Licence | MIT · open weights | [1] |
| Released | 11 August 2025 | [3] |
| Parameters | 106B total / 12B active (MoE) | [1] |
| Knowledge cutoff | December 2024 | [1] |

## Sources

1. [GLM-4.5V — Hugging Face model card](https://huggingface.co/zai-org/GLM-4.5V)
2. [Z.ai API pricing](https://docs.z.ai/guides/overview/pricing)
3. [GLM-V — GitHub repository](https://github.com/zai-org/GLM-V)

## Overview

GLM-4.5V is the open-weight vision-language model in Z.ai's (Zhipu / GLM) GLM-V line, released on August 11, 2025. It is a Mixture-of-Experts model with 106B total parameters and 12B activated per token, built on top of the GLM-4.5-Air-Base text foundation. GLM-4.5V handles images (up to 4K resolution, arbitrary aspect ratio), video, multi-image prompts, and documents such as PDFs and slide decks, and it can output precise bounding-box grounding for elements in a scene.

Like the earlier GLM-4.1V-9B-Thinking, GLM-4.5V ships with a toggleable thinking mode: users can switch between fast direct answers and a deeper chain-of-thought pass for harder visual reasoning, OCR, chart and document parsing, video understanding, and GUI-agent tasks (screen reading, icon detection, desktop operation). Z.ai reports state-of-the-art results among similarly sized open models across 42 public vision-language benchmarks.

The weights are released under the MIT license on Hugging Face (zai-org/GLM-4.5V) and the GLM-V GitHub repo, allowing commercial use and fine-tuning. GLM-4.5V is also served through the Z.ai API platform and third parties such as OpenRouter, with an exposed context window of roughly 64K tokens and up to 16K tokens of output.

## Benchmarks

- MMBench V1.1 (thinking): 88.2% ([source](https://arxiv.org/html/2507.01006v5))
- MMStar (thinking): 75.3% ([source](https://arxiv.org/html/2507.01006v5))
- MMMU val (thinking): 75.4% ([source](https://arxiv.org/html/2507.01006v5))
- MMMU Pro (thinking): 65.2% ([source](https://arxiv.org/html/2507.01006v5))
- MathVista (thinking): 84.6% ([source](https://arxiv.org/html/2507.01006v5))
- AI2D (thinking): 88.1% ([source](https://arxiv.org/html/2507.01006v5))
- OCRBench (thinking): 86.5% ([source](https://arxiv.org/html/2507.01006v5))
- ChartQAPro (thinking): 64% ([source](https://arxiv.org/html/2507.01006v5))
- ChartMuseum (thinking): 55.3% ([source](https://arxiv.org/html/2507.01006v5))
- OSWorld (GUI agent, thinking): 35.8% ([source](https://arxiv.org/html/2507.01006v5))
- WebVoyager (GUI agent, thinking): 84.4% ([source](https://arxiv.org/html/2507.01006v5))

## Pricing

- Input: $0.60 / 1M tokens per 1M tokens
- Cached input: $0.11 / 1M tokens per 1M tokens
- Output: $1.80 / 1M tokens per 1M tokens

Z.ai API platform list price. Open weights (MIT) can also be self-hosted at no per-token cost.

Source: https://docs.z.ai/guides/overview/pricing

## Strengths

- Open weights under the permissive MIT license — free for commercial use and fine-tuning
- Efficient MoE design: 106B total parameters but only 12B activated per token
- Toggleable thinking mode balances fast responses against deeper multimodal reasoning
- Broad visual coverage: images up to 4K, video, multi-image, PDFs and slides in one pass
- Strong STEM and chart/document scores (MMMU, MathVista, AI2D, ChartQAPro)
- Native grounding with bounding-box output and GUI-agent control (OSWorld, WebVoyager)

## Best for

- Document, chart and long-PDF understanding and information extraction
- OCR and structured data extraction from images and plots
- Long-video segmentation and event recognition
- GUI agents: screen reading, icon detection and desktop operation assistance
- Visual grounding and spatial localization with bounding boxes
- Multi-image scene analysis, defect inspection and geo/context inference

## How to access

- [Z.ai API Platform](https://docs.z.ai/guides/overview/pricing) — model id `glm-4.5v`
- [OpenRouter](https://openrouter.ai/z-ai/glm-4.5v) — model id `z-ai/glm-4.5v`

## GLM-V (vision-language) versions

- [GLM-4.6V](https://ai-tldr.dev/models/glm-4-6v/) (8 December 2025)
- GLM-4.5V (11 August 2025) — this page
- [GLM-4.1V-9B-Thinking](https://ai-tldr.dev/models/glm-4-1v-thinking/) (1 July 2025)

## FAQ

### Is GLM-4.5V open source?

Yes. The weights are released under the permissive MIT license on Hugging Face (zai-org/GLM-4.5V) and the GLM-V GitHub repo, allowing commercial use, redistribution and fine-tuning.

### How big is GLM-4.5V?

It is a Mixture-of-Experts model with 106B total parameters and 12B activated per token, built on the GLM-4.5-Air-Base text foundation. The efficient MoE design keeps inference cost closer to a 12B model.

### What inputs does GLM-4.5V support?

Text plus visual inputs: images up to 4K resolution at any aspect ratio, video, multi-image prompts, and documents such as PDFs and slide decks. It can also output bounding-box grounding and drive GUI agents.

### What does GLM-4.5V cost to use?

On the Z.ai API platform it lists at $0.60 per million input tokens and $1.80 per million output tokens, with cached input at $0.11 per million. Because the weights are MIT-licensed, you can also self-host with no per-token fee.

## Links

- [GLM-4.5V — Hugging Face model card](https://huggingface.co/zai-org/GLM-4.5V)
- [GLM-V — GitHub repository](https://github.com/zai-org/GLM-V)
- [GLM-4.5V technical report (arXiv 2507.01006)](https://arxiv.org/html/2507.01006v5)
- [Z.ai API pricing](https://docs.z.ai/guides/overview/pricing)
- [GLM-4.5V on OpenRouter](https://openrouter.ai/z-ai/glm-4.5v)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/glm-4-5v/