Models / ZAI

ZAI

Deploy the latest GLM models on Together AI. Open-weight frontier coding, configurable thinking effort, and OpenAI-compatible APIs.

Why ZAI on Together AI?

Designed for production workloads that need 
consistent performance and operational control.

Frontier agentic coding, open weights

Z.ai's GLM models rank among the top open-source systems for agentic coding and multi-step reasoning. They ship under the MIT license with open weights, so you get frontier performance with full commercial freedom.

Tune compute to the task

Configurable thinking-effort levels let you trade reasoning depth against throughput depending on task complexity. Dial up for complex refactors or down for fast, cost-sensitive calls, all through one OpenAI-compatible API.

Enterprise-ready from day one

SOC 2 Type II certified, HIPAA compliant, and deployed on US-based infrastructure. Full model ownership with no data retention by default.

Meet the ZAI family

Explore top-performing models across text, image, video, code, and voice.

Chat

GLM-5.3

new

Chat

GLM-5.3-Flash

Chat

GLM-5.2

Chat

GLM-4.5-Air

Chat

GLM-4.6

Chat

GLM-4.7

Chat

GLM-5

Chat

GLM-5.1

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless Inference

  • Provisioned 
Throughput

  • Dedicated Model 
Inference

  • Dedicated Container 
Inference

Serverless Inference

A fully managed real-time or batch inference API with access to dozens of the most popular AI models.

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Provisioned 
Throughput

Reserved token capacity with SLA guarantees. Priced in PTUs, a normalized throughput unit. 

Best for

Production workloads

Reliability guarantees

Predictable pricing

Dedicated Model 
Inference

An inference endpoint backed by reserved, isolated compute resources and Together AI inference research.

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Dedicated Container 
Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines