GLM 4.5V
GLM 4.5V is a large language model made by Z.ai, added to the catalog on 11 Aug 2025. It has a context window of 65,536 tokens and costs $0.60 per 1M input tokens and $1.80 per 1M output tokens. It accepts text and images and produces text. Typical uses: enhance video understanding tasks, improve image question and answer systems and streamline document parsing processes.
Price checked · source: OpenRouter
What GLM 4.5V is
Discover Z.AI's GLM 4.5V, a vision-language model released in August 2025. This model excels in processing both text and images, offering a context window of up to 65,536 tokens. With its Mixture-of-Experts architecture, it supports complex tasks like video understanding, image Q&A, and document parsing. The model provides a unique hybrid inference mode, allowing users to toggle between deep reasoning and fast response modes. This flexibility makes it suitable for applications requiring both detailed analysis and quick answers.
Key features
- 106B parameters with 12B activated
- Hybrid inference mode for flexibility
- Supports text and image inputs
- 65,536 token context window
- Mixture-of-Experts architecture
Typical uses
- Enhance video understanding tasks
- Improve image question and answer systems
- Streamline document parsing processes
- Boost front-end web coding capabilities
- Advance spatial reasoning applications
GLM 4.5V pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.60 |
| Output, per 1M tokens | $1.80 |
| Cached input read, per 1M tokens | $0.11 |
No price change since it was added on 11 Aug 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0008 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.016 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.022 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.093 |
GLM 4.5V specifications
| Model id | z-ai/glm-4.5v |
|---|---|
| Version | glm-4.5v |
| Context window | 65,536 tokensAbout 49,152 English words |
| Max output | 16,384 tokens |
| Knowledge cutoff | 2024-12-31 |
| Added to catalog | 11 Aug 2025 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | No |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI is poised to revolutionize work, leisure, and creativity by amplifying human potential. In the workplace, it will automate repetitive tasks—freeing professionals for strategic, creative roles—and enable hyper-personalized learning, making skill development faster and more accessible. Remote collaboration tools powered by AI could foster global teamwork, while predictive analytics optimize workflows, boosting productivity without burnout. For leisure, AI-driven personalization will curate experiences—from tailored entertainment recommendations to immersive virtual adventures—that cater to individual tastes, making downtime more enriching. Smart home systems and AI companions could also reduce daily friction, allowing people to focus on relaxation. Creativity stands to gain most: AI acts as a collaborative partner, generating novel ideas, refining artistic works, or even co-creating with humans. From music composition to design, it expands possibilities, democratizing creation tools so anyone can innovate. Ultimately, AI’s greatest impact may be liberating humanity from drudgery, letting us redirect energy toward meaningful pursuits—work that fulfills, leisure that recharges, and creativity that inspires.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.