Z.ai models
Which Z.ai models can you run on Modal?
Z.ai
GLM 5.3 Flash
A natively multimodal model for coding, agents, and long-context workloads.
Text VisionZ.ai
GLM 5.3
A natively multimodal model for coding, agents, and long-context workloads.
TextZ.ai
GLM 5.3 Flash NVFP4
A natively multimodal model for coding, agents, and long-context workloads, quantized to NVIDIA’s NVFP4 format.
Text VisionZ.ai
GLM 5.3
Z.ai's GLM-5.3 flagship coding model in Modal's NVFP4 quantization: a 753B sparse-attention MoE with 40B active parameters, 1M context, and three reasoning effort levels.
TextZ.ai
GLM 5.2 NVFP4
Z.ai's GLM-5.2 flagship in NVIDIA's NVFP4 quantization: a 753B sparse-attention MoE with 40B active parameters, 1M context, and MIT weights for Blackwell GPUs.
TextZ.ai
GLM 5.2 FP8
Z.ai's official FP8 checkpoint of GLM-5.2: a 753B sparse-attention MoE with 40B active parameters, a solid 1M context, configurable effort levels, and MIT weights.
Text
| Model | Architecture | Context | Modalities | Input / Output |
|---|---|---|---|---|
| GLM 5.3 Flash | 320B MoE | 1M | Text · Image | $0.45 / $1.50 |
| GLM 5.3 | 753B MoE | 1M | Text | $1.40 / $4.40 |
| GLM 5.3 Flash NVFP4 | 320B MoE | 1M | Text · Image | $0.15 / $0.50 |
| GLM 5.3 | 753B MoE · 40B active | 1M | Text | Dedicated only |
| GLM 5.2 NVFP4 | 753B MoE · 40B active | 1M | Text | Dedicated only |
| GLM 5.2 FP8 | 753B MoE · 40B active | 1M | Text | Dedicated only |
| GLM 4.7 | 358B MoE · 32B active | 200K | Text | Dedicated only |
All prices per million tokens. Dedicated Endpoint compute is billed by the second. See compute pricing.
Latest updates

Scaling Intelligence: A landmark commission and exhibition

Sandbox resourcing: burst, don't reserve
Why you're paying for capacity you aren't using, and how to pay only for what you use.

Modal becomes a gVisor maintainer
Modal runs upwards of 40 million gVisor containers every day. Here's why we bet on it, what we've built into it, and where we want to take it next.
