GLM 4.5
GLM 4.5 is a large language model made by Z.ai, added to the catalog on 25 Jul 2025. It has a context window of 131,072 tokens and costs $0.60 per 1M input tokens and $2.20 per 1M output tokens. It accepts text and produces text. Typical uses: improve complex reasoning tasks, generate accurate code snippets and enhance agent-based applications.
Price checked ยท source: OpenRouter
What GLM 4.5 is
Z.AI's GLM 4.5, released on July 25, 2025, is designed for agent-based applications. With a context window of 128k tokens, it excels in text-to-text tasks. The model features a Mixture-of-Experts architecture, enhancing reasoning, code generation, and agent alignment. It offers hybrid inference modes, allowing users to switch between 'thinking' for complex reasoning and 'non-thinking' for quick responses. Control the reasoning behavior with the 'reasoning' parameter. This flexibility makes GLM 4.5 suitable for diverse applications where reasoning and quick response are essential.
Key features
- 128k token context window
- Mixture-of-Experts architecture
- Hybrid inference modes
- Enhanced reasoning capabilities
- Agent alignment support
Typical uses
- Improve complex reasoning tasks
- Generate accurate code snippets
- Enhance agent-based applications
- Optimize quick response systems
GLM 4.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.60 |
| Output, per 1M tokens | $2.20 |
| Cached input read, per 1M tokens | $0.11 |
No price change since it was added on 25 Jul 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.017 |
| 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 4.5 specifications
| Model id | z-ai/glm-4.5 |
|---|---|
| Version | glm-4.5 |
| Context window | 131,072 tokensAbout 98,304 English words |
| Max output | 98,304 tokens |
| Knowledge cutoff | 2024-12-31 |
| Added to catalog | 25 Jul 2025 |
| Input types | text |
|---|---|
| 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 promises to positively upend the very fabric of our lives, transforming work, leisure, and creativity. In the workplace, it will act as a powerful co-pilot, automating tedious tasks and augmenting human intelligence. This will free us from drudgery, allowing us to focus on strategic thinking, complex problem-solving, and meaningful collaboration, fundamentally shifting our value from execution to innovation. Leisure will become profoundly personalized and immersive. AI could curate bespoke entertainment, craft unique travel experiences, and even generate interactive stories tailored to our moods. This moves us from passive consumption to active, bespoke engagement. Creativity will be supercharged as AI becomes a collaborative partner. Artists can use it to explore novel aesthetics, musicians to compose intricate scores, and writers to overcome creative blocks. By handling technical execution, AI empowers us to focus on the core of creativity: the spark of a new idea, pushing the boundaries of human imagination further than ever before.