Claude Sonnet and Dome
Run Claude Sonnet 5.5 from two providers under one name.
Sonnet is where many agent teams settle: the code reviewer, the docs writer, the support agent. The risk is drift. One config change and a busy agent is on Opus. Dome pins agents to Sonnet and keeps it answering when Anthropic doesn't.
How Dome helps
Dome provides model brokering and routing for Claude Sonnet
Anthropic first, Bedrock next
Every Sonnet call tries Anthropic at priority 0. Bedrock picks up the ones that fail, under the same model name.
An agent that stays on Sonnet
Tag Sonnet connections with a family attribute. A rule on the agent refuses every model outside it.
$300 a month, all providers
The quota sits on the pool, so it counts Anthropic and Bedrock together. Past $300, Sonnet calls stop until next month.
Get started
Sonnet with failover in five steps
Tag both Sonnet connections, pool them, pin the code reviewer, then set the monthly cap.
01
Connect Anthropic
The family: sonnet tag is what the pinning rule checks. The key itself never reaches an agent.
$ dome models add sonnet-55-anthropic \--provider anthropic \--model claude-sonnet-5-5 \--api-key "$ANTHROPIC_API_KEY" \--attributes '{"family":"sonnet"}' \--gateway prod-gateway02
Connect Amazon Bedrock
Bedrock takes AWS keys, so this one is a dashboard step: region, us.anthropic.claude-sonnet-5-5, and the same family tag. The CLI has no flag for AWS keys.
03
Pool them for failover
The pool is named for the model. A new Sonnet is a member swap. No agent needs a release.
$ dome models pool create claude-sonnet-5-5 \--failover-max all --gateway prod-gateway$ dome models pool member add claude-sonnet-5-5 sonnet-55-anthropic --priority 0$ dome models pool member add claude-sonnet-5-5 sonnet-55-bedrock --priority 104
Point your agent at the Gateway
The Anthropic SDK works as is. Point it at the Gateway with the code reviewer's Dome key.
import anthropicclient = anthropic.Anthropic(base_url=GATEWAY_URL, api_key=DOME_AGENT_KEY)client.messages.create(model="claude-sonnet-5-5",max_tokens=2048,messages=[{"role": "user", "content": "Review this diff."}],)05
Cap the spend
A pool quota counts every call through the pool, whichever provider answers.
$ dome quotas set --subject pool --pool claude-sonnet-5-5 \--unit provider_usd --limit 300 --window monthly
Commands and rules tested against a Dome workspace on October 1, 2026. For anything about Claude Sonnet itself, see Anthropic's documentation.
Rules
Keep an agent on Sonnet
Applied to one agent with --agent, this refuses any connection not tagged as Sonnet. The code reviewer can't reach Opus, whatever model name it sends.
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)unless { resource has family && resource.family == "sonnet" };Try it
One call, two outcomes
Switch the caller or the argument and watch the same call decide differently. Every decision lands in audit.
Model
- Agentcode-reviewer is registered and active
- Callerd.chen verified
- RuleConnection is tagged family: sonnet
- Quota$88 of $300 this month
Agent workflow
Bringing it together
Connecting Claude Sonnet 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
FAQ
Common questions
Which providers serve Claude Sonnet through Dome?
Anthropic's API, with Amazon Bedrock as the fallback. Claude on Vertex AI isn't available through Dome.
What happens when a new Sonnet version ships?
Add a connection for the new model id and swap it into the pool. Agents keep sending the pool's name.
Can I stop an agent from using a pricier model?
Yes. Tag connections with an attribute, and a rule on the agent refuses anything without it.
Explore
More of what Dome works with
Provider
OpenAI
The OpenAI API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
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
Okta
Okta tokens verified on every agent call, so rules and audit name the person each agent acted for.
Read moreRuntime
LangGraph
LangGraph agents with their model calls on the Model Broker and their MCP tools on the Tool Gateway.
Read moreClient
Codex
Codex 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.
AI models for enterprise agents: failover, rules and quotas
Every model your agents call goes through the Model Broker. Pool providers for failover, decide who may call each model, and cap what it costs.
See them all