GLM 4.6
GLM 4.6 is a large language model made by Z.ai, added to the catalog on 30 Sep 2025. It has a context window of 204,800 tokens and costs $0.50 per 1M input tokens and $2.00 per 1M output tokens. It accepts text and produces text. Typical uses: generate polished front-end pages, enhance tool-using agents and support complex agentic tasks.
Price checked · source: OpenRouter
What GLM 4.6 is
Discover Z.AI's GLM 4.6, released on September 30, 2025. This text-to-text model offers a 200K token context window, allowing it to handle complex tasks with ease. With improved coding performance and advanced reasoning capabilities, GLM 4.6 excels in generating polished front-end pages and supports tool use during inference. It is designed to align better with human preferences, making it ideal for role-playing scenarios. Whether you're working with text input or output, this model integrates seamlessly within agent frameworks, enhancing tool-using and search-based agents.
Key features
- 200K token context window
- Improved coding performance
- Advanced reasoning capabilities
- Enhanced tool integration
- Refined human-like writing
Typical uses
- Generate polished front-end pages
- Enhance tool-using agents
- Support complex agentic tasks
- Improve role-playing scenarios
GLM 4.6 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.50 |
| Output, per 1M tokens | $2.00 |
| Cached input read, per 1M tokens | $0.10 |
No price change since it was added on 30 Sep 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.014 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.019 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.078 |
GLM 4.6 specifications
| Model id | z-ai/glm-4.6 |
|---|---|
| Version | glm-4.6 |
| Context window | 204,800 tokensAbout 153,600 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | 2025-03-31 |
| Added to catalog | 30 Sep 2025 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| 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 pillars of modern life. In work, it will automate repetitive drudgery, acting as a co-pilot that frees human talent for strategic thinking, empathy, and complex problem-solving. This shift redefines value from task completion to insightful judgment. Leisure will evolve from passive consumption into deeply interactive and personalized experiences. Imagine AI generating a bespoke film soundtrack or crafting a video game world that adapts to your emotions in real-time. Creativity will be democratized, with AI serving as a universal muse and brainstorming partner, lowering the barrier for anyone to compose music, generate art, or write stories. Ultimately, AI won’t replace the human spirit but will amplify it, fostering a future where our time is more meaningful, our experiences richer, and our creative potential truly boundless.
Compare GLM 4.6
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.