Mistral API and Dome
Mistral behind one Gateway, with every call governed. Put Mistral behind Dome and tag its connections region: eu. A rule then holds work done for EU staff to those connections, and Mistral Medium stands behind Large in one pool.
Dome provides model brokeringand routing for Mistral.
One Mistral key for every team
Dome stores the Mistral key and attaches it to each request. Agents present their own Dome keys, so revoking one leaves the rest running.
EU work on EU connections
Tag Mistral connections region: eu. A rule refuses any untagged connection for EU staff.
A smaller model as fallback
Pool Mistral Large with Mistral Medium behind it. When Large fails, the call goes to Medium.
Connect Mistralin three steps.
Add Large and Medium, pool them, and give your agents the Gateway URL.
Add the connections
The provider id is mistral. Dome uses https://api.mistral.ai/v1 and Mistral's own model ids.
shelldome models add mistral-large-eu \ --provider mistral \ --model mistral-large-latest \ --api-key "$MISTRAL_API_KEY" \ --attributes '{"region":"eu"}' \ --gateway prod-gateway dome models add mistral-medium-eu \ --provider mistral \ --model mistral-medium-latest \ --api-key "$MISTRAL_API_KEY" \ --attributes '{"region":"eu"}' \ --gateway prod-gatewayPool them
Large is priority 0 and Medium priority 1, and agents ask for the pool, mistral-large.
shelldome models pool create mistral-large \ --failover-max all --gateway prod-gateway dome models pool member add mistral-large mistral-large-eu --priority 0dome models pool member add mistral-large mistral-medium-eu --priority 1Point your agent at the Gateway
Swap Mistral's base URL for the Gateway's, and the Mistral key for the agent's Dome key.
pythonfrom openai import OpenAI client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create( model="mistral-large", messages=[{"role": "user", "content": "Draft a reply to this employee question."}],)
EU staffstay on EU connections.
When the person an agent acts for is in eu-staff, only connections tagged region: eu are allowed. Dome reads the group from that person's verified token.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when { principal has act_as && principal.act_as.groups.contains("eu-staff")}unless { resource has region && resource.region == "eu" };Bringing it alltogether.
Connecting Mistral 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
MistralProvider
OpenRouterProviderCommon questionsabout Mistral.
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.