Zhipu

GLM 5.2

z-ai
Chat

GLM 5.2 running in a Trusted Execution Environment (TEE). Z.AI's flagship model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.

Beta

Modalities

In / out price

$1.75 / $5.75

per 1M

Context

524K

Max output

33K

Released

Jun 16, 2026

Updated

Jul 17, 2026

Privacy

3 / 3

End-to-end encrypted routing

E2EE tier

  1. Anonymous
  2. Private
  3. E2EE
  • Your client encrypts the prompt before it leaves your environment.
  • Only verified secure compute can decrypt the request for inference.

Moderation

Not specified

No model-level moderation classification is recorded in this catalog.

Data retention

Not specified

The catalog reports encryption or isolation separately from retention.

Features

5
Streaming
Tool calling
Reasoning
Web search
Code optimized

Routing

2

Anonrouter hosted

Routed through AnonRouter's gateway with metadata-only logging.

Provider direct

Requests egress directly to the provider runtime.

USD per 1M tokens from the Venice models API.

Providers & sources

1 route

Uptime

30d