Coding Model · Z.ai
GLM-5.2
GLM-5.2 is Z.ai's reasoning-capable coding model, strong on long-horizon coding and agentic work. It was succeeded by GLM-5.3 on August 18, 2026 — the same base model with new post-training, a 1M-token context, and the same price — and Z.ai publishes a 5.2 to 5.3 migration guide. Teamday now runs GLM-5.3 through the Pi harness via OpenRouter or Together.
At a glance (verified 2026-09-02)
- Vendor
- Z.ai
- Type
- Coding Model
- Pricing
- Together lists $1.40 input / $0.26 cached / $4.40 output per 1M tokens.
Best for
How to use GLM-5.2 in Teamday
GLM-5.2 has been succeeded by GLM-5.3 in Teamday's chat model picker — pick GLM-5.3 on the Pi harness, routed through OpenRouter (OPENROUTER_API_KEY) or Together (TOGETHER_API_KEY).
Frequently asked questions
How much does GLM-5.2 cost?
Together lists $1.40 per 1M input tokens, $0.26 cached, and $4.40 per 1M output tokens. Through OpenRouter, pricing varies by the selected upstream provider.
What is GLM-5.2 good at?
Long-horizon coding and agentic work; it is a reasoning-capable, OpenAI-compatible coding model.
Is GLM-5.2 still current?
No — Z.ai released GLM-5.3 on August 18, 2026: the same base model with new post-training, 1M context, and the same $1.40 / $0.26 cached / $4.40 per 1M pricing on Z.ai (OpenRouter z-ai/glm-5.3, Together zai-org/GLM-5.3). Z.ai publishes a 5.2 to 5.3 migration guide.
How do I run GLM-5.2 in Teamday?
Teamday now runs its successor, GLM-5.3, on the Pi harness in the chat model picker, routed via OpenRouter or Together with your own API key.
Related
- GLM-5.3 — Coding Model
- Kimi K3 — Coding Model
- DeepSeek V4 Pro — Coding Model
- Qwen 3.7 Plus — Coding Model
GLM-5.2 is one of the models Teamday's AI employees already run — no API keys, no infrastructure.
Hire your first AI employee →