Question 1

How is GLM served?

Accepted Answer

Through Ollama Cloud. GLM is one of a curated set of hosted open-weight models we enable, so you do not provision hardware for it and requests go to Ollama. The Ollama page carries the current roster across both hosted and local.

Question 2

Can I self-host GLM instead?

Accepted Answer

Where the model is available to pull, yes. Self-hosted Ollama runs on hardware you control and is open-ended: any model Ollama can serve will work, which is the path for teams whose data cannot leave their own network.

Question 3

Why choose an open-weight model over a frontier one?

Accepted Answer

Cost at volume, and control. Open-weight models price differently from frontier APIs, which matters when query volume is high, and the option to move the same model onto your own hardware later keeps you from being locked to one vendor.

Question 4

What is GLM good at?

Accepted Answer

Agent work. GLM scores well on tool calling and multi-step tasks among open-weight models, which is what the invoice and exception agents do all day. Served through Ollama Cloud, so there is no hardware to provision.

Question 5

Which other models can I run alongside GLM?

Accepted Answer

Any of them, and more than one at a time. CommerceShip runs ChatGPT, Claude, Gemini, Mistral, and Muse as frontier models, and DeepSeek, Gemma, GLM, Kimi, Llama, MiniMax, Nemotron, and Qwen as open-weight models, served through Ollama Cloud or on your own hardware. Route routine work to one model and heavier analysis to another, and if a provider is rate-limited or down, the run moves to a fallback and completes.

Question 6

What access does CommerceShip need to GLM?

Accepted Answer

The connection uses scoped credentials limited to the record types the integration works with, and you choose which fields are included. Credentials are encrypted at rest and stored separately from your operational data. Revoke the connection from either side at any time and the access ends with it.

Question 7

How is my data protected?

Accepted Answer

TLS in transit and AES-256 at rest, with tenant isolation enforced by row-level security in the database. Role-based permissions control who on your team can see cost data or change carrier settings, and automated actions are written to an audit log. CommerceShip is pursuing SOC 2 Type II certification. The security page carries the full detail.

Run supply chain AI on GLM

GLM Integration Capabilities

How the GLM integration works

Choose GLM

Assign GLM to the work

Ask and act

GLM Integration FAQs

Use GLM with no hardware to set up

Other Models