Kimi and Dome

1. 01

   Connect Moonshot AI

   Moonshot's API is OpenAI-compatible at api.moonshot.ai. Dome keeps its key and sends it as a bearer token.

   $ dome models add kimi-moonshot \
     --provider moonshot \
     --model kimi-k3 \
     --api-key "$MOONSHOT_API_KEY" \
     --attributes '{"family":"kimi"}' \
     --gateway prod-gateway

2. 02

   Connect Together AI and Fireworks AI

   Same model, each host's own id. Tag them the same way.

   $ dome models add kimi-together \
     --provider together \
     --model moonshotai/Kimi-K3 \
     --api-key "$TOGETHER_API_KEY" \
     --attributes '{"family":"kimi"}' \
     --gateway prod-gateway
    
   $ dome models add kimi-fireworks \
     --provider fireworks \
     --model accounts/fireworks/models/kimi-k3 \
     --api-key "$FIREWORKS_API_KEY" \
     --attributes '{"family":"kimi"}' \
     --gateway prod-gateway

3. 03

   Pool them for failover

   Moonshot first, then Together AI, then Fireworks AI. A coding agent asks for kimi-k3 and gets whichever answers.

   $ dome models pool create kimi-k3 \
     --failover-max all --gateway prod-gateway
    
   $ dome models pool member add kimi-k3 kimi-moonshot --priority 0
   $ dome models pool member add kimi-k3 kimi-together --priority 1
   $ dome models pool member add kimi-k3 kimi-fireworks --priority 2

4. 04

   Point your agent at the Gateway

   Swap the base URL for the Gateway and the key for the agent's Dome key. Nothing else in the client changes.

   from openai import OpenAI
    
   client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)
   client.chat.completions.create(
       model="kimi-k3",
       messages=[{"role": "user", "content": "Refactor this module to remove the global state."}],
   )

5. 05

   Cap the spend

   The cap is on the pool, so moving between hosts doesn't reset it.

   $ dome quotas set --subject pool --pool kimi-k3 \
     --unit provider_usd --limit 400 --window monthly

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

forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)
when { resource has family && resource.family == "kimi" }
unless { principal has act_as && principal.act_as.roles.contains("engineer") };