Claude Haiku and Dome
Run Claude Haiku 4.5 as the fast default for high-volume agents. Haiku is the volume model. Classifiers, routers and triage agents call it thousands of times a day, so an outage is a queue and a runaway loop is a bill. Dome spreads it across two providers, caps each agent's tokens, and makes it the only model contractors reach.
Dome provides model brokeringand routing for Claude Haiku.
Volume without a single point of failure
Pool Anthropic and Bedrock under claude-haiku-4-5. A provider outage costs one retry, not a backlog.
Haiku as the floor for some callers
Tag Haiku connections as small. A rule keeps contractors on them and refuses everything larger.
A token cap per agent
Cap the batch classifier at 5M tokens a day. A runaway job stops at its own ceiling.
Haiku with failoverin five steps.
Two connections tagged small, a pool, then a token cap on the batch classifier.
Connect Anthropic
tier: small marks it as the model contractors may use. Triage agents call with their own keys; the Anthropic key stays put.
shelldome models add haiku-45-anthropic \ --provider anthropic \ --model claude-haiku-4-5 \ --api-key "$ANTHROPIC_API_KEY" \ --attributes '{"tier":"small"}' \ --gateway prod-gatewayConnect Amazon Bedrock
Bedrock's Haiku id is us.anthropic.claude-haiku-4-5-20251001-v1:0. AWS keys go in through the dashboard, with tier: small on this connection too.
Pool them for failover
A failed classification retries on Bedrock instead of joining a backlog.
shelldome models pool create claude-haiku-4-5 \ --failover-max all --gateway prod-gateway dome models pool member add claude-haiku-4-5 haiku-45-anthropic --priority 0dome models pool member add claude-haiku-4-5 haiku-45-bedrock --priority 1Point your agent at the Gateway
A triage agent written against the OpenAI SDK only needs the Gateway URL and its Dome key.
pythonfrom openai import OpenAI client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create( model="claude-haiku-4-5", messages=[{"role": "user", "content": "Classify this ticket: billing, bug or other."}],)Cap tokens per agent
An agent quota counts every model call that agent makes, through any pool.
shelldome quotas set --subject agent --agent batch-classifier \ --dimension llm --unit tokens --limit 5000000 --window daily
Contractors get Haikuand nothing larger.
When the person an agent acts for is in the contractors group, only connections tagged small are allowed. The group arrives in their identity token.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when { principal has act_as && principal.act_as.groups.contains("contractors")}unless { resource has tier && resource.tier == "small" };One call,two outcomes.
Switch the caller or the argument and watch the same call decide differently, with every decision landing in audit.
Model
agent intake-agent · acting as contractor.lee
llm:invoke(model: "claude-haiku-4-5")
- Agentintake-agent is registered and active
- Callercontractor.lee verified, groups: contractors
- RuleConnection is tagged tier: small
- Quota1.2M of 5M tokens today
DecisionAllowed
Bringing it alltogether.
Connecting Claude Haiku to registered agents, tools, and identity in Dome completes a governed agent application.
Acting for
Control point
GatewayEvery call decided and audited
RulesGuardsQuotas
Models
Common questionsabout Claude Haiku.
More of whatDome works with.
Provider
OpenAI
The OpenAI API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
MCP server
GitHub
The GitHub MCP server behind the Tool Gateway, with rules that decide each call on its owner and repository.
Identity
Okta
Okta tokens verified on every agent call, so rules and audit name the person each agent acted for.
Runtime
LangGraph
LangGraph agents with their model calls on the Model Broker and their MCP tools on the Tool Gateway.
Client
Claude Code
Claude Code on a Dome Gateway with per-developer sign-in, rules on every tool call, and audit by name.
Agent service
TinyFish
TinyFish's web agents behind the Tool Gateway, with rules that decide each run on the site it targets.
Talk with ourFDE team.
Or start free, and register your first agent in minutes. Connect it through a gateway, give it rules, and see every call it makes in one audit trail.
Talk with our FDE team
Our engineers design, build and run governed agents for the part of your business you want to change. You see what they deliver.
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.