Switch Inference Models
Change the model on an existing provider route with a runtime update or a fresh sandbox recreation. The command requires both the provider and model even when the provider does not change.
Check the Current Route
Read the live route before changing it.
Use the provider ID in the output with the new model ID.
Change the Model at Runtime
Deep Agents uses the fresh recreation path for model changes.
This path keeps the OpenShell route and /sandbox/.deepagents/config.toml aligned.
To validate a new model before replacing the current sandbox, onboard it under a new name and make it the default after validation.
Account for Shared Gateways
OpenShell exposes one inference route per gateway. Every registered sandbox on the same gateway, including stopped sandboxes, must record the same provider and model. NemoClaw exits before changing state when the requested model conflicts with another sandbox on the gateway.
Align the sandboxes to one route, remove a sandbox you no longer need, or onboard a sandbox with another NEMOCLAW_GATEWAY_PORT.
Verify the Change
Read the route again after the switch.
Use a sandbox-route verification when you also need to prove that the agent can reach the model.
Related Topics
- View the Active Inference Route to inspect the current provider and model.
- Switch Providers to move to another provider family.
- Verify the Sandbox Inference Route to test the agent path.