Announcing Dome Managed Agents.

Try it now

DeepSeek API and Dome

Use DeepSeek for the work that can, with rules that keep it from the work that can't. Connect DeepSeek to Dome and tag each connection with where it runs. People handling regulated data are held to connections tagged residency: us, and everyone else can call DeepSeek directly. Together AI hosts the same V4 Pro.

Dome provides model brokeringand routing for DeepSeek.

No DeepSeek key on the client

Dome keeps DeepSeek's key and adds it to each request. Agents carry Dome keys, and only Dome talks to DeepSeek.

Residency by rule

Tag each connection with where it runs. A rule keeps people who handle regulated data on the connections you approved.

The same model, another host

Together AI hosts DeepSeek V4 Pro too. Pool them and Together answers whatever DeepSeek can't.

Connect DeepSeekin three steps.

Add DeepSeek and Together's copy of V4 Pro, pool them, and route agents through the Gateway.
  1. Add the connections

    The provider id is deepseek. Dome uses https://api.deepseek.com/v1 and DeepSeek's own model ids; Together uses its own.

    shell
    dome models add deepseek-direct \  --provider deepseek \  --model deepseek-v4-pro \  --api-key "$DEEPSEEK_API_KEY" \  --gateway prod-gateway
    dome models add deepseek-together \  --provider together \  --model deepseek-ai/DeepSeek-V4-Pro-0813 \  --api-key "$TOGETHER_API_KEY" \  --attributes '{"residency":"us"}' \  --gateway prod-gateway
  2. Pool them

    DeepSeek goes first and Together second, and agents call the pool, deepseek-v4-pro.

    shell
    dome models pool create deepseek-v4-pro \  --failover-max all --gateway prod-gateway
    dome models pool member add deepseek-v4-pro deepseek-direct --priority 0dome models pool member add deepseek-v4-pro deepseek-together --priority 1
  3. Point your agent at the Gateway

    Swap the base URL for the Gateway and DeepSeek's key for the agent's, and OpenAI-compatible code runs as before.

    python
    from openai import OpenAI
    client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create(    model="deepseek-v4-pro",    messages=[{"role": "user", "content": "Refactor this function and explain the change."}],)

Regulated data stayson approved connections.

When the person an agent acts for is in regulated-data, only connections tagged residency: us are allowed. Everyone else can use DeepSeek directly.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when {  principal has act_as &&  principal.act_as.groups.contains("regulated-data")}unless { resource has residency && resource.residency == "us" };

One call,two outcomes.

Switch the caller or the argument and watch the same call decide differently, with every decision landing in audit.

Connection

agent claims-assistant · acting as m.ortiz
llm:invoke(model: "deepseek-together")
  1. Agentclaims-assistant is registered and active
  2. Callerm.ortiz verified, groups: regulated-data
  3. RuleConnection is tagged residency: us
DecisionAllowed

Bringing it alltogether.

Connecting DeepSeek to registered agents, tools, and identity in Dome completes a governed agent application.
Dome

Acting for

Control point

GatewayEvery call decided and audited
RulesGuardsQuotas

Common questionsabout DeepSeek.

How does Dome connect to DeepSeek?
Through DeepSeek's OpenAI-compatible API at https://api.deepseek.com/v1. Only Dome sends the DeepSeek key, as a bearer header.
Which DeepSeek models can I use?
Any id DeepSeek's API accepts, such as deepseek-v4-pro or deepseek-flash.
Does the residency tag change where DeepSeek processes data?
No. The tag is your label, read by rules. DeepSeek's terms decide where it processes data.
Can I run DeepSeek models without calling DeepSeek's API?
Yes. Together and DeepInfra serve DeepSeek V4 Pro under their own model ids, and a pool can put them behind DeepSeek or in its place.

More of whatDome 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.
MCP server

GitHub

The GitHub MCP server behind the Tool Gateway, with rules that decide each call on its owner and repository.
Identity

Microsoft Entra ID

Entra access tokens verified on every agent call, so rules read app roles and audit names the person.
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.

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.

Every agent you run, under one system of control.