OpenRouter and Dome

1. 01

   Add the connection

   The provider id is openrouter. Dome uses https://openrouter.ai/api/v1 and OpenRouter's own model ids.

   $ dome models add gpt-oss-openrouter \
     --provider openrouter \
     --model openai/gpt-oss-120b \
     --api-key "$OPENROUTER_API_KEY" \
     --attributes '{"approved":true}' \
     --gateway prod-gateway

2. 02

   Pool it behind Groq

   Groq serves the same open-weight model and goes first. OpenRouter answers when it can't.

   $ dome models pool create gpt-oss-120b \
     --failover-max all --gateway prod-gateway
    
   $ dome models pool member add gpt-oss-120b gpt-oss-groq --priority 0
   $ dome models pool member add gpt-oss-120b gpt-oss-openrouter --priority 1

3. 03

   Point your agent at the Gateway

   Code written for OpenRouter's API keeps working. Change the base URL to the Gateway and the key to the agent's.

   from openai import OpenAI
    
   client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)
   client.chat.completions.create(
       model="gpt-oss-120b",
       messages=[{"role": "user", "content": "Summarize these release notes."}],
   )

Commands and rules tested against a Dome workspace on October 1, 2026. For anything about OpenRouter itself, see OpenRouter's documentation.

forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)
unless { resource has approved && resource.approved == true };