GLM 5.2 is live
Get Instant Access
Run Z.ai's newest flagship — and any open model — from one API key.
One API. Every model. No surprises.
Call GLM 5.2 with one key — no GLM Coding Plan, no setup, no hosting. Every trending model, instantly.
GLM 5.2 runs on infrastructure built for real workloads, dependable uptime and low latency across long agentic sessions.
Flat-rate plans with unlimited tokens. Run repository-scale work at full context without a prompt counter or a per-token meter.
Flat pricing with unlimited tokens
- Access to DeepSeek, Kimi-K2 and GLM 5.2
- Access any model - no limit on size!
- Up to 4 concurrent connections
- Up to 32K context
- Access any model - no limit on size!
- Upto 8 concurrent connections
- Up to 256K context
- 1 agent runtime
- Larger sandbox environment
- Persistent Storage