GLM-5
Z.ai's open-weights GLM-5 model family built for coding and long-horizon agentic tasks, also offered through the Z.ai API.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code
Use cases
About GLM-5
GLM-5 is listed in our models & local runtimes category and is aimed at builders. Z.ai's open-weights GLM-5 model family built for coding and long-horizon agentic tasks, also offered through the Z.ai API. Pricing, as the maker states it: Open weights (repository Apache-2.0); Z.ai API pricing not verified yet. Maturity: Mature. We last checked the official link on 2026-10-21.
What is GLM-5?
GLM-5 is Z.ai's open-weights model family for coding and long-horizon agentic work, and the GitHub repository now covers GLM-5, 5.1, 5.2, 5.3 and GLM-5.3-Flash. GLM-5.2 brought a stable 1M-token context and coding with selectable thinking effort, with IndexShare cutting per-token compute at long context.
GLM-5.3 keeps the 5.2 base and improves complex coding and long-horizon tasks through post-training, while GLM-5.3-Flash is a new, more efficient base with hybrid sparse and linear attention. The weights can be run yourself, and the models are also served through the Z.ai API platform and the z.ai chat app.
Sources: the official README and our directory listing, checked 2026-10-21. Official site: z.ai/blog/glm-5.2.
Who is GLM-5 for?
Developers who want a strong open-weights model for coding agents and long agentic tasks, self-hosted or via API.
GLM-5 at a glance
- Open source: Yes (Apache License 2.0)
- GitHub: zai-org/GLM-5 · 7,367 stars · 991 forks (as of Oct 21, 2026)
Key features
- Open weights for coding and agentic tasks
- 1M-token context (GLM-5.2 and later)
- Selectable thinking effort
- GLM-5.3-Flash efficient hybrid-attention variant
- Also available through the Z.ai API
GLM-5 FAQ
What is GLM-5?
GLM-5 is Z.ai's open-weights model family for coding and long-horizon agentic work, and the GitHub repository now covers GLM-5, 5.1, 5.2, 5.3 and GLM-5.3-Flash. GLM-5.2 brought a stable 1M-token context and coding with selectable thinking effort, with IndexShare cutting per-token compute at long context.
Who is GLM-5 for?
Developers who want a strong open-weights model for coding agents and long agentic tasks, self-hosted or via API.
Is GLM-5 free?
GLM-5's pricing, as the maker states it: Open weights (repository Apache-2.0); Z.ai API pricing not verified yet. Check the official site for current plans.
Is GLM-5 open source?
Yes. GLM-5 is released under the Apache License 2.0, according to its GitHub repository.
What are alternatives to GLM-5?
Similar tools include pooled, Meta Muse Wonder, ASI:One, Sidekick, Oumi and MiroThinker.
GLM-5 ratings and reviews
Be the first to rate GLM-5: tap 1 to 5 stars below. A written review is optional.
GLM-5 alternatives
Other models & local runtimes tools in our directory. See all models & local runtimes tools →
pooled
Peer-to-peer LLM inference in the browser: pool your laptops, phones and other devices into a room to run large open models for chat and coding agents, with no GPU server.
Meta Muse Wonder
Meta's new models for personal and professional agent tasks, available via Meta Model API and Muse Code.
ASI:One
Agentic LLM and chat app from Fetch.ai built to reason, plan and call other agents on the ASI Alliance network.
Sidekick
Native macOS app for chatting offline with a local LLM that can draw on your files, folders and websites.
Oumi
Open platform for fine-tuning, evaluating and deploying open agentic LLMs and VLMs.
MiroThinker
Deep research agent and open models tuned for complex research and forecasting tasks.
Related lists
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built GLM-5? Add this badge to your README or site. It links back to this page. About badges
