Cohere API and Dome
Cohere Command behind one Gateway, with every call governed. Dome talks to Cohere through its OpenAI compatibility API, so Command and Embed sit behind the same Gateway as every other model. Mark the connections legal approved, and work done for legal stays on them.
Dome provides model brokeringand routing for Cohere.
Cohere's key stays with Dome
No agent is handed the Cohere key. Each one authenticates with a Dome key of its own.
Approved connections for legal work
Tag the connections your legal team approved. A rule refuses every other connection when an agent acts for someone in legal.
Chat and embeddings
Command models answer chat completions and Embed models answer embeddings. Both run through the same Gateway.
Connect Coherein three steps.
Add Command and Embed connections, pool Command for a fallback, and repoint agents.
Add the connections
The provider id is cohere. Dome uses Cohere's compatibility endpoint, https://api.cohere.ai/compatibility/v1, and Cohere's own model ids.
shelldome models add command-a-plus-cohere \ --provider cohere \ --model command-a-plus-05-2026 \ --api-key "$COHERE_API_KEY" \ --attributes '{"approved_for":"legal"}' \ --gateway prod-gateway dome models add command-a-cohere \ --provider cohere \ --model command-a-03-2025 \ --api-key "$COHERE_API_KEY" \ --attributes '{"approved_for":"legal"}' \ --gateway prod-gatewayPool them
Command A Plus answers first and Command A second, and agents send the pool's name.
shelldome models pool create command-a-plus \ --failover-max all --gateway prod-gateway dome models pool member add command-a-plus command-a-plus-cohere --priority 0dome models pool member add command-a-plus command-a-cohere --priority 1Point your agent at the Gateway
Change the base URL to the Gateway and the key to the agent's own, and OpenAI-compatible SDKs need nothing else.
pythonfrom openai import OpenAI client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create( model="command-a-plus", messages=[{"role": "user", "content": "List the indemnity clauses in this contract."}],)
Legal work stayson approved connections.
When the person an agent acts for is in legal, only connections tagged approved_for: legal are allowed. Their group comes from the identity token the agent passes on.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when { principal has act_as && principal.act_as.groups.contains("legal")}unless { resource has approved_for && resource.approved_for == "legal" };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 contract-reviewer · acting as e.walsh
llm:invoke(model: "command-a-plus")
- Agentcontract-reviewer is registered and active
- Callere.walsh verified, groups: legal
- RuleConnection is tagged approved_for: legal
DecisionAllowed
Bringing it alltogether.
Connecting Cohere 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
CohereProvider
OpenAIProviderCommon questionsabout Cohere.
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.