GLM 5
GLM 5 is a large language model made by Z.ai, added to the catalog on 11 Feb 2026. It has a context window of 204,800 tokens and costs $1.00 per 1M input tokens and $3.20 per 1M output tokens. It accepts text and produces text. Typical uses: enhance large-scale programming tasks, facilitate full-system construction and automate complex agent workflows.
Price checked · source: OpenRouter
What GLM 5 is
Z.ai's GLM 5, released on February 11, 2026, is an open-source foundation model designed for expert developers. With a significant context length of 204,800 tokens, it excels in text-to-text tasks, enabling complex systems design and long-horizon workflows. The model supports various input and output modalities, making it versatile for large-scale programming tasks. Key features include advanced agentic planning and iterative self-correction, allowing for full-system construction and autonomous execution. This model is engineered to rival leading closed-source models, providing production-grade performance for developers looking to enhance their coding capabilities.
Key features
- Open-source foundation model
- Supports 204,800 token context length
- Advanced agentic planning capabilities
- Iterative self-correction for improved performance
- Designed for complex systems and workflows
Typical uses
- Enhance large-scale programming tasks
- Facilitate full-system construction
- Automate complex agent workflows
GLM 5 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.00 |
| Output, per 1M tokens | $3.20 |
| Cached input read, per 1M tokens | $0.20 |
No price change since it was added on 11 Feb 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0015 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.028 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.036 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.155 |
GLM 5 specifications
| Model id | z-ai/glm-5 |
|---|---|
| Version | glm-5-20260211 |
| Context window | 204,800 tokensAbout 153,600 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 11 Feb 2026 |
| 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 fundamentally reshape society by liberating us from the mundane. In the realm of work, automation will likely eradicate repetitive drudgery, allowing humans to pivot toward strategic thinking, empathy-driven roles, and complex problem-solving. This shift could redefine productivity, focusing on value created rather than hours logged. Creativity stands to be democratized; AI tools will lower barriers to entry, enabling anyone to manifest their visions through art, music, or code. It acts not as a replacement, but as a collaborative partner that accelerates ideation and refines execution. Consequently, leisure will undergo a renaissance. As efficiency rises, the rigid boundary between work and life may soften, granting us more time for exploration and connection. Personalized entertainment and immersive virtual experiences will enrich our downtime. Ultimately, AI’s positive disruption lies in its potential to return agency to humanity, fostering a future where we spend less time surviving and more time thriving.
Compare GLM 5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.