GLM 5 Turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.

ChatZhipu203k tokens$1.3081 / $4.3602 · 1M

z-ai/glm-5-turbo

Context
203k tokens
Completion cap
131,072
Tools
Yes
JSON
Yes
Released
2026-03-15

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5-turbo",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is GLM 5 Turbo?
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks. GLM 5 Turbo runs on the Geek Hub API (OpenAI-compatible). Model id: z-ai/glm-5-turbo.
Is GLM 5 Turbo free?
No. Input is $1.3081 per 1M tokens and output is $4.3602 per 1M tokens on Geek Hub (markup included).
What is the context length of GLM 5 Turbo?
GLM 5 Turbo has a 203k tokens context window. It supports up to 131,072 completion tokens.
Does GLM 5 Turbo support tool calling and structured outputs?
GLM 5 Turbo accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GLM 5 Turbo released?
GLM 5 Turbo was released on 2026-03-15.

More models from Zhipu