Models
Employees point their AI client at Gateway instead of the model provider, so every model request they make arrives somewhere you control. The Models section is where you decide what happens to it.
Four decisions. The first three live on tabs under Models in the Workforce dashboard; spend has its own page under Manage.
A seventh tab, Advanced, holds the controls that apply to your whole organization at once: vendor regions, zero data retention, request tags, and model migrations. It is still gated, so those settings live in the Gateway console for now. See Advanced.
What an employee’s client needs
Three values, and they are the same three in every AI client.
Prefer default_routing. Model choice then lives in your routing policy rather than in a config file on every laptop, and changing which model a team uses stops being a fleet-wide edit. A request that names a model still gets access checks, guardrails, and budget enforcement; it skips only the routing decision.
Sending an Anthropic client to the OpenAI base URL is the most common setup mistake. Connect employee AI clients covers the per-client values and how they reach a machine.
What a request passes through
Order matters, because it determines which of your controls an employee can and cannot route around.
- Access. Blocklist rules and your vendor restrictions drop the models and vendors your organization does not allow. This runs before routing, so no strategy change reaches a blocked model.
- Guardrails. The prompt is screened for sensitive data and injection attempts, then redacted, blocked, or recorded according to your rules.
- Routing. The Group’s routing policy, or the organization default, picks a model from what is left and a vendor to serve it.
- Budget. An exhausted budget refuses the request with a
402before any provider is called, so a blocked request costs nothing. - Response. The completion is screened on the way back, and the whole request is written to LLM calls with the model, tokens, routing outcome, and cost.
Employees see none of this unless something fires. A refusal comes back as an ordinary API error in whatever client they are using.
Next steps
Pick a strategy and attach it to a Group or to the whole organization
Set which vendors and models your organization allows, and block the rest
Screen prompts and completions for sensitive data and injection attempts
Vendor regions, data retention, tags, and migrations