AI models for enterprise agents
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.
Any model your providers serveConnect it, pool it for failover, and decide who may call it.
| Integration | Kind | Governed by | Standard |
|---|---|---|---|
Fable 5.1 from Anthropic and Amazon Bedrock in one failover pool, open to one group and capped by quota. | Models | Model Broker | Anthropic API |
Haiku 4.5 from Anthropic and Amazon Bedrock in one failover pool, as the default model for high-volume agents and contractors. | Models | Model Broker | Anthropic API |
Opus 5.5 from Anthropic and AWS Bedrock in one failover pool, with rules on who calls it and quotas on what it costs. | Models | Model Broker | Anthropic API |
Sonnet 5.5 from Anthropic and Amazon Bedrock in one failover pool, with agents pinned to it and quotas on spend. | Models | Model Broker | Anthropic API |
DeepSeek V4 Pro from Together AI and DeepInfra in one failover pool, with regulated work kept off DeepSeek's own API. | Models | Model Broker | OpenAI API |
Gemini on Vertex AI behind the Model Broker: Flash with a fallback model, Pro kept to one group, spend capped by quota. | Models | Model Broker | OpenAI API |
Gemma 4 31B from DeepInfra and NVIDIA NIM in one failover pool, with contractors kept on it and a cap on daily calls. | Models | Model Broker | OpenAI API |
GPT-6 from OpenAI and Azure OpenAI in one failover pool, with rules on which deployment handles which work. | Models | Model Broker | OpenAI API |
gpt-oss-120b from Groq, Cerebras and Together AI in one failover pool, with unattended jobs kept on open weights. | Models | Model Broker | OpenAI API |
Grok 4.7 from xAI with OpenRouter as fallback in one pool, kept to the research team. | Models | Model Broker | OpenAI API |
Kimi K3 from Moonshot AI, Together AI and Fireworks AI in one failover pool, kept to the people who need it. | Models | Model Broker | OpenAI API |
Llama 3.3 70B from Groq, Together AI and SambaNova in one failover pool, limited to the teams that need it. | Models | Model Broker | OpenAI API |
Mistral Large 3 from Mistral and NVIDIA NIM in one failover pool, with EU work kept on EU connections. | Models | Model Broker | OpenAI API |
Qwen 3.8 from Together AI and DeepInfra in one failover pool, with an agent pinned to it and a cap on its spend. | Models | Model Broker | OpenAI API |
Any model, behind a pool
Connect a model from each provider, pool the connections, and agents send the pool's name. The list below is a convenience: any model id your provider accepts works.
- 1
Connect the model
Add one connection per provider and model, and the provider key stays in Dome.
shelldome models add opus-55-anthropic \ --provider anthropic --model claude-opus-5-5 \ --api-key "$ANTHROPIC_API_KEY" --gateway prod-gateway - 2
Pool it for failover
Members are tried in priority order, and the pool is named for the model.
shelldome models pool create claude-opus-5-5 --failover-max all --gateway prod-gatewaydome models pool member add claude-opus-5-5 opus-55-anthropic --priority 0dome models pool member add claude-opus-5-5 opus-55-bedrock --priority 1 - 3
Send the pool's name
Agents call the Gateway with their own 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-opus-5-5", messages=messages)
Commands tested against a Dome workspace on September 30, 2026.
Common questions
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.
LLM router guide
What an LLM router does, and what to ask of one before your agents depend on it.