Add Z.ai (GLM) models
TIE AI Gateway
TIE now routes requests to Zhipu AI (Z.ai) GLM models. Select a model by passing a zai/-prefixed name to /v1/chat/completions, the same way you select any other provider.
{
"model": "zai/glm-4.6",
"messages": [{ "role": "user", "content": "Hello" }]
}Available models
| Model | Notes |
|---|---|
zai/glm-5.2 |
Latest flagship |
zai/glm-5.1 |
Previous flagship |
zai/glm-5-turbo |
Faster, lower-cost tier |
zai/glm-5 |
General-purpose |
zai/glm-4.7 |
Strong agentic coding and reasoning |
zai/glm-4.7-flash |
Lightweight, low-latency |
zai/glm-4.6 |
200K context window |
zai/glm-4.5 |
Prior generation |
GLM models support tool calling and a thinking reasoning mode. They run through Z.ai’s OpenAI-compatible API, so existing request and response handling needs no changes.
Configuration
Set ZAI_API_KEY to enable the provider. When Z.ai is the only configured provider, glm-4.6 becomes the default model. Override the default with DEFAULT_MODEL=zai/glm-5.2.
Query GET /info to confirm which models are active on your instance.
See the chat completions reference for the full provider list.