Announcing Dome Managed Agents.

Try it now

LLM providers for AI agents

Connect a provider once. Its key stays in Dome, and every agent call to it is authorized, metered and audited.

Any OpenAI-compatible providerPlus Anthropic, Amazon Bedrock, Vertex AI and Azure OpenAI natively.

Integration catalog
IntegrationKindGoverned byStandard
AI21
ProvidersModel BrokerOpenAI API
Amazon Bedrock behind the Model Broker: AWS credentials held in Dome, Converse calls signed per request, Claude pooled with Anthropic.
ProvidersModel BrokerBedrock
The Claude API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
ProvidersModel BrokerAnthropic API
Azure OpenAI deployments behind the Model Broker: the key held in Dome, region rules on who reaches which deployment.
ProvidersModel BrokerOpenAI API
The Cerebras API behind the Model Broker: open models with the key held in Dome, Fireworks for failover and full audit.
ProvidersModel BrokerOpenAI API
Cohere's Command and Embed models behind the Model Broker: the key held in Dome, approval rules per team, every call audited.
ProvidersModel BrokerOpenAI API
Databricks Model Serving behind the Model Broker: the token held in Dome, a vendor fallback in the same pool, every call audited.
ProvidersModel BrokerOpenAI API
The DeepInfra API behind the Model Broker: open models with the key held in Dome, Together AI for failover and full audit.
ProvidersModel BrokerOpenAI API
The DeepSeek API behind the Model Broker: the key held in Dome, residency rules on regulated work, every call audited.
ProvidersModel BrokerOpenAI API
The Fireworks AI API behind the Model Broker: open models with the key held in Dome, Together AI for failover and full audit.
ProvidersModel BrokerOpenAI API
Gemini on Vertex AI behind the Model Broker: the service account held in Dome, every call authorized, metered and audited.
ProvidersModel BrokerOpenAI API
The Groq API behind the Model Broker: open-weight models with the key held in Dome, a fallback provider and full audit.
ProvidersModel BrokerOpenAI API
The Mistral API behind the Model Broker: the key held in Dome, region rules on EU work, every call audited.
ProvidersModel BrokerOpenAI API
The Moonshot AI Kimi API behind the Model Broker: the key held in Dome, trials limited to one team, every call audited.
ProvidersModel BrokerOpenAI API
NVIDIA NIM behind the Model Broker: self-hosted containers first, hosted NIM as failover, and rules on who may use the hosted API.
ProvidersModel BrokerOpenAI API
1–15 of 22

Every provider works the same way

Add a connection with the provider's key, then point agents at the Gateway. OpenAI- and Anthropic-compatible clients both work.
  1. 1

    Add the connection

    The key goes into Dome's vault, per workspace and connection, and is injected at call time.

    shell
    dome models add claude-fable \  --provider anthropic --model claude-fable-5-1 \  --api-key "$ANTHROPIC_API_KEY" --gateway prod-gateway
  2. 2

    Point agents at the Gateway

    The agent's Dome key replaces the provider key.

    python
    from openai import OpenAI
    client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)

Commands tested against a Dome workspace on September 30, 2026.

Common questions

Where are provider keys stored?
They are kept in Dome's vault, per workspace and connection, and injected at call time, so agents never hold them.
Can I use a provider that isn't listed?
Yes, if it serves the OpenAI-compatible API. Add it as an OpenAI-compatible connection with its base URL.
Can one agent use several providers?
Yes. Pool connections from different providers, and the agent sends one model name.

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.

Every agent you run, under one system of control.