Coding Model · Z.ai
GLM-5.3
GLM-5.3 is Z.ai's current reasoning-capable coding model, released August 18, 2026 as the successor to GLM-5.2: the same base model with new post-training, a 1M-token context window, and the same price. TeamDay runs it through the Pi harness via OpenRouter (z-ai/glm-5.3) or Together (zai-org/GLM-5.3).
At a glance (verified 2026-09-02)
- Vendor
- Z.ai
- Type
- Coding Model
- Context window
- 1M tokens
- Pricing
- Z.ai lists $1.40 input / $0.26 cached / $4.40 output per 1M tokens.
- OpenRouter ID
- z-ai/glm-5.3
Best for
How to use GLM-5.3 in TeamDay
Pick GLM-5.3 on TeamDay's Pi harness, routed through OpenRouter (OPENROUTER_API_KEY) or Together (TOGETHER_API_KEY).
Frequently asked questions
How much does GLM-5.3 cost?
Z.ai lists $1.40 per 1M input tokens, $0.26 cached, and $4.40 per 1M output tokens — unchanged from GLM-5.2. It is hosted on OpenRouter as z-ai/glm-5.3 and on Together as zai-org/GLM-5.3.
What changed from GLM-5.2 to GLM-5.3?
GLM-5.3 is the same base model with new post-training and a 1M-token context window, at the same price. Z.ai publishes a 5.2 to 5.3 migration guide for existing integrations.
Is there a cheaper GLM-5.3 tier?
Yes — GLM-5.3-Flash (released August 26, 2026) lists $0.075 input (a 50% promo) / $0.015 cached / $0.25 output per 1M tokens and adds native vision.
How do I run GLM-5.3 in TeamDay?
Select it on the Pi harness in the chat model picker, routed via OpenRouter or Together with your own API key.
Related
- GLM-5.2 — Coding Model
- Kimi K3 — Coding Model
- DeepSeek V4 Pro — Coding Model
- Qwen 3.7 Plus — Coding Model
GLM-5.3is one of the models TeamDay's AI employees already run — no API keys, no infrastructure.
Hire your first AI employee →