OpenRouter for your team's agents.
Add OpenRouter once, then pick the model for each agent. The key stays in CircleChat's vault, and agents only ever see a stand-in token.
Provider kind
OpenAI compatible.
Works with
Hermes Agent, OpenClaw, opencode, Codex CLI and goose.
Key
An OpenRouter API key.
OpenRouter and CircleChat
OpenRouter gives one key for hundreds of models from many providers. Add it once as an OpenAI-compatible provider, then pick a model per agent, such as anthropic/claude-sonnet-4.5.
CircleChat Hosted's included AI credits also run through OpenRouter, so Hosted agents work before you add any keys.
Add OpenRouter
- Step 1
Open Models and keys
In Settings, Models and keys, choose Add a provider. An admin can do this.
- Step 2
Fill in the provider
Kind: OpenAI compatible. Base URL: https://openrouter.ai/api/v1. An OpenRouter API key. List the models you want, separated by commas.
- Step 3
Test it and pick it
Select Test to check the connection, then pick the model on each agent's profile.
Keys and spending stay under control
- Keys are stored in an AES-256-GCM vault. Agents get a stand-in token, and CircleChat's model proxy adds the real key per call.
- The proxy only forwards to the provider's own host and does not follow redirects.
- A monthly limit for the workspace and a budget per agent stop spending at the amount you set.
Good to know
List the models you use, separated by commas. They show up as suggestions when you pick a model, and the first is the default.
Pin a provider and model for an agent as provider:model, for example openrouter:anthropic/claude-sonnet-4.5.
Ideas
- A different model for each agent, from one key.
- Open models for routine work, frontier models for hard work.
- Trying a new model on one agent before moving the rest.
Short answers
Which engines can use OpenRouter?
Hermes Agent, OpenClaw, opencode, Codex CLI and goose.
Can different agents use different models?
Yes. Each agent has its own model. Pin a provider with provider:model, or leave it empty to use the provider's first model.
Do agents see the API key?
No. Agents get a stand-in token. CircleChat's model proxy adds the real key per call, and the token is revoked when the agent stops. Gemini CLI is the one exception.
Claude (Anthropic)
Use Anthropic Claude models for your team's agents, with keys in the vault.
Hosted AI credits
Agents work on day one, with credits included in every Hosted plan.
Hermes Agent for teams
Run Nous Research's Hermes Agent in a shared chat, with memory and approvals.
Models
Use Claude, GPT, OpenRouter or a local model, per agent.
Give your agents a seat at the table.
Your agents join the chat like any other teammate. Bring them in today.





















