GLMZhipu AIOpen weights
GLM 5 Turbo.
GLM 5 Turbo is Z.ai's model for fast inference in agent-driven environments. It is optimised for agent workflows with long execution chains, breaks down complex instructions, uses tools and supports scheduled and continuously running execution. It processes text with a context of about 200,000 tokens.
base_url="https://api.noirdoc.de/v1" model="z-ai/glm-5-turbo"
- Data centres in the EU
- § 203 confidentiality
- Zero retention
- List prices
Details.
Where the model runs, which rules apply and what it can do.
- Data centres in the EU TensorX Contracting party: TensorX Ltd. · based in Dublin, Ireland
- § 203 German Criminal Code (StGB)
- Confidentiality agreed with TensorX
- Weights
- Open weights
- Features
- Tools, Vision, Reasoning and JSON
Providers.
We offer GLM 5 Turbo through these providers.
Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
TensorX EU EU data centres (Ireland, Finland)
z-ai/glm-5-turbo Input 1.08 Cache Read 0.27 Output 3.60
More models.
Zhipu AI, now Z.ai, develops the GLM series of open models for reasoning and agentic tasks.
All GLM models → Model
€ · 1M tokens Input Cache Read Cache Write Output
TensorX Get started.
Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.
import os
from openai import OpenAI
client = OpenAI(
# one line, that's all
base_url="https://api.noirdoc.de/v1",
api_key=os.environ["NOIRDOC_API_KEY"],
)
response = client.chat.completions.create(
model="z-ai/glm-5-turbo", # provider & model
messages=[{"role": "user", "content": "Hello"}],
)