Skip to content

AI inference from Nuremberg

GLM inference in a Nuremberg data center. ChatGPT, Claude and Gemini when you need them.

GLM runs through our partner noris network in a certified Nuremberg data center. We operate the 2342.ai platform on our own infrastructure at the Deutschherrnkarree in Nuremberg; Core-Backbone provides colocation and network connectivity. External frontier models remain available with their respective data paths.

Contact us View model catalog
Infrastructure partner for GLM: noris network ↗ Colocation and network connectivity: Core-Backbone ↗ noris network certifications ↗

Traceable data paths

The model determines the data path – and you see it before use.

GLM carries the “Nuremberg data center” label in the model catalog. ChatGPT, Claude, Gemini and other external models remain available for other tasks. The model catalog, DPA and subprocessor list make each data path traceable.

workspace.open() mode.private_or_business() knowledge.connect() automation.run() budget.meter_usage()

2342.ai platform

Own infrastructure at the Deutschherrnkarree

The core platform runs on our own access-controlled infrastructure in Nuremberg. Core-Backbone provides colocation and network connectivity.

  • Platform operations in Nuremberg
  • Own server infrastructure
  • Colocation and network by Core-Backbone
  • TLS-encrypted connection

GLM data path

Inference through noris network

GLM runs through noris network in a certified Nuremberg data center. The stated certifications apply to noris network and its respective locations and services, not to 2342.ai or Core-Backbone.

  • Nuremberg inference location
  • Clearly labeled in the model catalog
  • Available through web, browser and API
  • Partner certifications can be verified

Model choice

External frontier models remain available

ChatGPT, Claude, Gemini and other model families remain available. Each uses the external data path identified before use.

  • Current model families
  • Data path visible before use
  • One shared access point
  • Shared usage recording

A data path with a real location

Choose a model, understand its data path, manage usage together.

01

Classify the task and protection need

Decide which data will be processed and which requirements apply to the task.

02

Choose data path and model

Choose GLM with inference through noris network in Nuremberg or ChatGPT, Claude or Gemini based on the task.

03

Manage access and usage

Manage roles, project, budget and API access together and keep usage traceable.

Where does GLM inference take place?

Through our partner noris network in a certified Nuremberg data center. The “Nuremberg data center” label in the model catalog shows this data path before use.

Do ChatGPT, Claude and Gemini remain available?

Yes. They remain available as external models in the catalog. For data that should be processed in Nuremberg, choose a correspondingly labeled model.

Can I use the same models with Claude Code, OpenCode or Codex CLI?

Yes. The tools connect through the 2342.ai API. Model choice, budget checks and usage recording therefore also work for coding workflows.

How can I tell where a model is processed?

The model catalog identifies the intended data path before use. GLM carries the “Nuremberg data center” label; other models use their documented external data path.

Are all models processed in Nuremberg?

No. GLM runs through noris network in Nuremberg. External model families such as ChatGPT, Claude and Gemini use their respective labeled data paths. Choose based on the task and required data path.