Announcing Dome Managed Agents.

Try it now

DeepInfra API and Dome

Open models on DeepInfra, with every call governed. DeepInfra hosts open models like DeepSeek and Gemma under one key. Connect it to Dome, tag connections with the region you approved, and an agent is refused on anything untagged. Together AI serves the same DeepSeek V4 Flash as a fallback.

Dome provides model brokeringand routing for DeepInfra.

The key stays put

Dome keeps DeepInfra's key and adds it to each outbound request. Agents hold Dome keys only, so a leaked agent key never exposes DeepInfra's.

Two hosts, one release

Together AI serves the same DeepSeek V4 Flash release. Put both in a pool and DeepInfra's failures land on Together.

Your tags, your rules

Tag each connection with the region you approved, and a rule refuses anything without the tag.

Connect DeepInfrain three steps.

Add DeepSeek V4 Flash on DeepInfra, pair it with Together AI, then hand agents the Gateway address.
  1. Add the connection

    The provider id is deepinfra. Dome uses https://api.deepinfra.com/v1/openai and DeepInfra's own model ids.

    shell
    dome models add deepseek-deepinfra \  --provider deepinfra \  --model deepseek-ai/DeepSeek-V4-Flash-0731 \  --api-key "$DEEPINFRA_API_KEY" \  --attributes '{"region":"us"}' \  --gateway prod-gateway
  2. Pool it with Together AI

    Add the same DeepSeek id on Together as a second connection, with DeepInfra going first.

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

    Keep your OpenAI-compatible code. Point it at the Gateway and hand it the agent's Dome key.

    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-flash",    messages=[{"role": "user", "content": "Summarize this claim file."}],)

Approvedregions only.

Applied to an agent, this refuses any connection not tagged region: us. A new connection stays out of reach until someone tags it.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)unless { resource has region && resource.region == "us" };

Bringing it alltogether.

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

Control point

GatewayEvery call decided and audited
RulesGuardsQuotas

Common questionsabout DeepInfra.

How does Dome connect to DeepInfra?
Through DeepInfra's OpenAI-compatible endpoint, https://api.deepinfra.com/v1/openai. Your key goes out as a bearer header from Dome, never from the agent.
Which model ids does DeepInfra use?
Repo-style ids with the publisher first, such as deepseek-ai/DeepSeek-V4-Flash-0731 or google/gemma-4-31B-it.
Does Dome know where a model runs?
Only what you tag. Connection attributes are your own vocabulary, and rules read them on every call.

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

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.

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.