/ Get started
Connect your AI models
The AgentWork team thinks with AI models you own, through your Claude subscription or API keys from the providers you choose, so model costs go straight to your account.
AgentWork does not resell model access. You connect your own subscription or API keys, and model usage is billed to you directly by the provider. Connections live in Settings → Models & Usage → Connections.
Connection options
| Connection | What you need | Notes |
|---|---|---|
| Claude subscription | A Claude Pro or Max plan | Agents work through Claude Code on your subscription's quota. |
| Anthropic | An API key from console.anthropic.com | Pay as you go. |
| OpenAI | An API key from platform.openai.com | Pay as you go. |
| Google Gemini | An API key from Google AI Studio | Pay as you go. |
| OpenRouter | An API key from openrouter.ai | One key for many models from many providers. |
| OpenAI-compatible endpoint | A public (HTTPS) address, and a key if it needs one | For a model proxy or gateway of your own. |
A ChatGPT subscription cannot be used as a connection yet. It is on our roadmap. For OpenAI models, use an OpenAI or OpenRouter API key for now.
Claude subscription
- On your computer, install Claude Code and run
claude setup-token. - Sign in with your Claude account. The command prints a token.
- In AgentWork, open Connections → Add connection → Claude subscription and paste the token.
The token is stored encrypted in your instance and is never shown in full again. The team's usage counts against your subscription's quota. When the quota runs out, the agents affected move to the repair bay in the Office and carry on once the quota is back.
API keys
Create a key on the provider's site and paste it in Add connection. AgentWork checks the key and lists the models it can use. We recommend a key just for AgentWork, so its usage is easy to follow and it can be revoked without affecting anything else.
Your own endpoint
If you run a model gateway of your own that speaks the OpenAI API, choose Custom (OpenAI-compatible) and enter its address. It must be reachable from the internet over HTTPS. Addresses on a local network or your own computer are refused for security.
One provider or two?
One connection is enough to start. Two providers from different model families, for example a Claude subscription plus an OpenAI API key, give the best results: QA can then review the work with a different model from the one that did it, which catches mistakes typical of one model. See QA review.
Choosing models per role
In Models & Usage → Routing, you choose the model for each role: specialists, reviewer, second reviewer and more, including fallback models for when the main one is unavailable. After onboarding, every role uses the model you picked in the connection step.
Costs and limits
- Model costs are billed to your account by the provider, at their prices and terms.
- A budget per project. Every project has a token budget: by default 500 thousand (Quick), 1.5 million (Standard) and 4 million (Deep). Change these in Models & Usage → Budgets.
- An 80% warning. When a project reaches 80% of its budget, a warning is recorded. When the budget runs out, the project stops and its lead tells you in the chat. Retry incomplete tasks grants one more budget and the tasks resume where they stopped.
- Follow usage in Models & Usage: model calls, tokens per agent and per project, and the work that uses the most tokens.