Requesty
Z AI logo

Z AI

Z AI (formerly Zhipu AI) provides advanced large language models with strong agentic and coding capabilities. Requesty routes to 5 Z AI models starting at $0.60 per 1M input tokens with context windows up to 200K tokens. One API key, OpenAI-compatible SDK, no markup.

All Z AI models

ModelContextMax OutputInput/1MOutput/1MCapabilitiesSWE-Bench
GLM-5.1
200K128K$1.40$4.40
πŸ‘πŸ§ πŸ”§βš‘
β€”
GLM-5
200K128K$1.00$3.20
πŸ‘πŸ§ πŸ”§βš‘
β€”
GLM-4.7
200K128K$0.60$2.20
πŸ§ πŸ”§
β€”
GLM-4.5
131K98K$0.60$2.20
πŸ§ πŸ”§
β€”
GLM-4.6
200K128K$0.60$2.20
πŸ§ πŸ”§
β€”

About Z AI on Requesty

How many Z AI models are available through Requesty?
Requesty routes to 5 Z AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Z AI model?
The cheapest Z AI model starts at $0.60 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Z AI pricing?
No. Requesty passes through exactly what Z AI charges. You pay the same per-token rates as going direct β€” plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Z AI models?
Z AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Z AI models hosted?
Z AI models are hosted in πŸ‡ΈπŸ‡¬ Singapore. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI β€” filter by region on the Z AI rows in the models explorer.