Question 1

Can I run Ollama alongside a frontier provider?

Accepted Answer

Yes. The provider is configuration, so routine questions can run on Ollama while heavier analysis routes to a frontier provider. A fallback chain with health checks handles the case where one provider is unavailable.

Question 2

What happens when a model is retired?

Accepted Answer

Retired model IDs are remapped to current equivalents automatically, and configured providers are validated against their live model listings. A model that disappears upstream does not appear as a failed agent run.

Question 3

Can I bring my own Ollama account?

Accepted Answer

Yes. Provider credentials are configured per tenant, so requests run through your own Ollama account and usage counts against your plan. A deployment with no override configured falls back to the default provider.

Question 4

Does using Ollama change what CommerceShip can do?

Accepted Answer

No. The agent tools, the data they read, and the actions they can take are the same whichever provider serves the model. The provider is a setting. What changes is cost, latency, and where inference physically runs.

Question 5

What is the difference between Ollama and Ollama Cloud?

Accepted Answer

Ollama runs models on hardware you control, on a server in your own network. Ollama Cloud runs open-weight models on hosted infrastructure, so you get them without buying GPUs. The integration is identical and the choice is a configuration setting.

Question 6

Does my data leave my infrastructure?

Accepted Answer

With self-hosted Ollama, no. The prompts and the operational data stay inside your network. Use it where sending shipment or customer data to a third party is not permitted. With Ollama Cloud, requests go to Ollama, so it is a hosted service and should be evaluated as one.

Question 7

Which models can I run?

Accepted Answer

Two rosters. Hosted through Ollama Cloud: GLM, Kimi, MiniMax, Gemma, and Nemotron. Locally hosted on your own hardware: Llama, Qwen, DeepSeek-R1, and Gemma. Swapping between them is a configuration change, and the roster moves as the open-weight field does, so ask us for the current list.

Question 8

Which other models can I run alongside Ollama?

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 9

What access does CommerceShip need to Ollama?

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 10

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 where you choose

Ollama Integration Capabilities

How the Ollama integration works

Connect Ollama

Choose the models

Ask and act

Ollama Integration FAQs

Run your models on Ollama

Models You Can Run