Together AI API and Dome
Open models on Together AI, with every call governed. One Together AI key reaches a long list of open models. Connect it to Dome and each agent gets the families you pick: a rule keeps a support agent on Llama, and DeepInfra answers Llama calls when Together can't.
Dome provides model brokeringand routing for Together AI.
New models wait for you
Dome holds the Together key and sends it as a bearer token. A model Together adds reaches no agent until you add a connection for it.
Same model, second provider
DeepInfra serves the same Llama 3.3 70B. Pool the two and a failed call on Together goes to DeepInfra.
One family per agent
Tag each connection with its model family. A rule keeps an agent on Llama, whatever else Together serves.
Connect Together AIin three steps.
Add one Together model, back it with DeepInfra, then point agents at the Gateway.
Add the connection
The provider id is together. Dome uses https://api.together.xyz/v1 and Together's own model ids.
shelldome models add llama-together \ --provider together \ --model meta-llama/Llama-3.3-70B-Instruct-Turbo \ --api-key "$TOGETHER_API_KEY" \ --attributes '{"family":"llama"}' \ --gateway prod-gatewayPool it with DeepInfra
Add the same model on DeepInfra as a second connection. Members are tried in priority order, and agents send the pool's name.
shelldome models pool create llama-3.3-70b \ --failover-max all --gateway prod-gateway dome models pool member add llama-3.3-70b llama-together --priority 0dome models pool member add llama-3.3-70b llama-deepinfra --priority 1Point your agent at the Gateway
Any OpenAI-compatible client works. The agent's Dome key replaces the Together key.
pythonfrom openai import OpenAI client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create( model="llama-3.3-70b", messages=[{"role": "user", "content": "Draft a reply to this support ticket."}],)
This agentuses Llama only.
Applied to one agent with --agent, this refuses any connection not tagged family: llama. Kimi and DeepSeek stay one connection away, and out of reach.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)unless { resource has family && resource.family == "llama" };Bringing it alltogether.
Connecting Together AI to registered agents, tools, and identity in Dome completes a governed agent application.
Acting for
Agent
Control point
GatewayEvery call decided and audited
RulesGuardsQuotas
Models
Common questionsabout Together AI.
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
OpenAI Agents SDK
OpenAI Agents SDK agents with their models 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.