Claude API and Dome
One Anthropic key. Every agent call governed.
Connect the Claude API to Dome once. Agents reach Claude with Dome keys of their own, Anthropic's key stays in Dome's vault, and rules decide each call before Anthropic sees it.
How Dome helps
Dome provides model brokering and routing for Anthropic
Anthropic's key, out of reach
Dome injects the x-api-key header at call time. Every read of the key is audited, and no agent ever holds it.
Agents authenticate as themselves
Each agent calls with its own Dome key. Revoke the agent and its calls stop, with the Anthropic key untouched.
A ceiling on every loop
Calls are metered to the agent and the person it acted for. A quota halts a runaway Claude loop at the limit you set.
Get started
Connect Anthropic in two steps
Add the connection, then change your agent's base URL. Existing Anthropic and OpenAI SDK code keeps working.
01
Add the connection
Any Claude model id works. Add one connection per model you want agents to reach.
$ dome models add claude-fable \--provider anthropic \--model claude-fable-5-1 \--api-key "$ANTHROPIC_API_KEY" \--gateway prod-gateway02
Point your agent at the Gateway
The Anthropic SDK takes the Gateway URL as its base. OpenAI-compatible clients use the same URL with /v1.
import anthropicclient = anthropic.Anthropic(base_url=GATEWAY_URL, api_key=DOME_AGENT_KEY)client.messages.create(model="claude-fable",max_tokens=1024,messages=[{"role": "user", "content": "Draft a reply to this ticket."}],)
Commands and rules tested against a Dome workspace on September 30, 2026. For anything about Anthropic itself, see Anthropic's documentation.
Rules
Frontier models by group
Tag a connection with an attribute and write a rule against it. This one keeps frontier connections to one team, whichever agent is calling.
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when { resource has tier && resource.tier == "frontier" }unless { principal has act_as && principal.act_as.groups.contains("ml-research")};Agent workflow
Bringing it together
Connecting Anthropic to registered agents, tools, and identity in Dome completes a governed agent application.
Acting for
Control point
Gateway
- Rules
- Guards
- Quotas
Every call decided and audited
Models
Provider
Anthropic
This page
Model
Claude Opus
See how
FAQ
Common questions
How does Dome authenticate to Anthropic?
With your Anthropic API key, stored in Dome's vault and sent as the x-api-key header on each call. Agents never see it.
Which Claude models can I use?
Any model id Anthropic accepts. The dashboard suggests current ones, from Claude Fable 5.1 to Claude Haiku 4.5.
Do I need to change my agent code?
Two settings: the base URL and the key. The Anthropic SDK and OpenAI-compatible clients both work.
Can Anthropic's server-side tools run through Dome?
No. Dome blocks Anthropic's MCP connector and code execution betas, so every tool call goes through the Gateway and its rules.
Explore
More of what Dome works with
Model
Claude Fable
Fable 5.1 from Anthropic and Amazon Bedrock in one failover pool, open to one group and capped by quota.
Read moreMCP server
GitHub
The GitHub MCP server behind the Tool Gateway, with rules that decide each call on its owner and repository.
Read moreIdentity
Microsoft Entra ID
Entra access tokens verified on every agent call, so rules read app roles and audit names the person.
Read moreRuntime
OpenAI Agents SDK
OpenAI Agents SDK agents with their models on the Model Broker and their MCP tools on the Tool Gateway.
Read moreClient
Claude Code
Claude Code on a Dome Gateway with per-developer sign-in, rules on every tool call, and audit by name.
Read moreAgent service
TinyFish
TinyFish's web agents behind the Tool Gateway, with rules that decide each run on the site it targets.
Read moreNext steps
Talk with our FDE team
Our forward deployed engineers work with your platform team to get your agents into production and under control: the first one governed on your own systems, and a pattern your teams can repeat for every agent after it.
No card required to start. Register your first agent in minutes.
LLM providers for AI agents: one governed path to every model
Connect a provider once. Its key stays in Dome, and every agent call to it is authorized, metered and audited.
See them all