Skip to main content
Connect model providers once, decide who can use which model, and see what it costs. Members just pick a model; they never handle keys.

​
Set it up

1

Add a provider

In the OpenWork Cloud dashboard, open AI Gateway > AI Providers > Add provider and pick one from the catalog.
Add Anthropic: shared API key, who can use it, and which models
2

Choose who can use it

Keep Everyone in the organization, or add specific teams and people. Pick all models or only some.
Anthropic provider row: all models, everyone, ready
3

Limit models (optional)

Under Who can use models, choose Only models you provide so members can’t add their own keys.
Who can use models set to Only models you provide
4

Set spend limits

On Limits, give a team or person a daily, weekly, or monthly USD amount. Pause or warn when it runs out.
New spend limit: Design team, $20 a day and $300 a month
5

Test it

A member picks the model in the desktop app or OpenWork Web and sends a prompt. Granted models sync automatically.
Self-hosting? Enable OpenWork Gateway first.

​
What you get

Keys stay on the server

One org credential per provider, or per-member Google sign-in for Vertex AI.

Access per team

Group models, then grant each group to the org, a team, or a person.

Spend limits

USD allowances with hard limits and optional increase requests.

Usage by person

Per-member keys attribute tokens and cost. See Counting usage.
Already run LiteLLM or Bifrost? Keep it. See AI Gateway vs LiteLLM vs Bifrost.

​
FAQ

OpenAI, Anthropic, Google, Google Vertex AI (including Claude on Vertex), Azure, Amazon Bedrock, Mistral, OpenRouter, and catalog providers with an OpenAI-compatible API. Models come from the models.dev catalog.
AI Gateway routes your providers through OpenWork with access rules, limits, and usage tracking. OpenWork Models is a managed subscription with no keys, billed separately. Bring your own keys syncs an org provider to members and the app calls it directly; see Managed LLM provider. The MCP Gateway is separate: it shares skills and connections, not models.
Costs are estimates from reported tokens and public prices, or a provider-reported cost when returned. They are not your provider’s bill. See Token costs.
Shared keys are on the Team plan and spend observability is on Enterprise, for Cloud and self-hosted alike. Providers bill model usage. See Pricing and licensing.