Skip to main content
The Users & Teams tab answers one question: who can use which models, how much they can spend, and how much they’ve spent. You change access on each provider; this tab shows the result for every person and team in one place.

​
Where to find it

In OpenWork Cloud, open AI Gateway and select the Users & Teams tab. Seeing it needs three permissions: View Gateway providers, View Gateway usage, and View usage limits. Organization owners and admins have them by default.

​
What the tab shows

At the top, a row for Everyone in your organization shows what every member gets, including people who join later. Below it, switch between People and Teams, or use Filter by name. Each row shows: Spend is an estimate from public model prices, not your provider’s bill. See Token costs.

​
Open a team

Click a team to see only its members. A strip at the top shows the team’s providers, limit, and spend, with Set a team limit or Edit team limit. No teams yet? Click Create a team. Teams are managed in Members.

​
Open a person

Click a person to see:
  • Last 31 days: their total estimated spend.
  • What they can use: each provider they can use. Click Change in AI Providers to change it.
  • Spend limit: whether they’re Within the limit, Over the limit, or Paused, with Set a limit or Edit.
  • Models they use: spend per model.

​
Give people models

Access is set on each provider, not on the person. To give someone models:
1

Open the provider

Go to AI Gateway › AI Providers and click the provider. To add a new one, click Add a provider.
2

Choose who can use it

Under Who can use it, turn on Everyone in the organization, or turn it off and click Add person or Add team.
3

Choose which models

Under Models, pick All models (for example All Anthropic models), or Only the ones I pick and select them.
4

Save

Click Save changes. Members’ apps pick up the new models on their next sync.
A person can use a provider’s models if any route gives them access: everyone, one of their teams, or them directly. OpenWork Models is different: when it’s on, everyone in the organization can use it.

​
Shared key or each person’s own account

Each provider has a Key setting:
  • Shared API key: you paste one key, and everyone with access uses it. The key stays on OpenWork’s servers; members never see it.
  • Each member signs in: each person connects their own account, such as Google sign-in for Vertex AI, AWS IAM Identity Center for Amazon Bedrock, Microsoft Entra ID for Microsoft Foundry, or a personal key for LiteLLM. Only some providers support this.

​
Stop members from adding their own keys

On AI Gateway › AI Providers, the Who can use models row shows your organization’s policy. Click Change:
  • Only models you provide: members see only what you set up in AI Gateway and OpenWork Models, and can’t add their own provider keys. You can still allow Admins may still add their own keys on their device.
  • Any model: members can also add their own provider keys on their device. Your AI Gateway models still show up.
The same dialog has Free starter model (Auto), which lets members fall back to OpenWork’s free, rate-limited model. Changes apply to every member, on desktop and the web, the next time they open OpenWork.

​
Set limits

To cap spend for everyone, a team, or a person, see Limits. The Limit column on this tab shows which limit applies to each row.

​
Model groups, credential sets and access grants

You may see these terms in permissions, the API, or a member’s Technical details in My Library. They’re the pieces behind the screens above:
  • A model group is a set of models from one provider: all of them, or only the ones you picked.
  • A credential set is how those models are paid for: the shared API key, or each member’s own sign-in.
  • An access grant gives a model group to everyone in the organization, a team, or one person.
The Who can use it, Models and Key sections on a provider set all three for you.