Skip to main content
Model tools register LLM upstreams the gateway proxies — Anthropic, OpenAI, Azure OpenAI, Google, Bedrock, hosted OpenAI-compatible vendors (Groq, Mistral, Together, Fireworks, DeepSeek, xAI, Perplexity, Cohere, OpenRouter, Cerebras, NVIDIA, DeepInfra, SambaNova, AI21, Databricks), and self-hosted endpoints — and group them into routing pools. Pools give agents one logical name that fans out across providers with priority, weighting, and failover. Models share workspace scope, gateway placement, and credential handling with Tools. Use models for inference endpoints; use tools for MCP servers.

Model CRUD

dome_model_list

List LLM model connections in the active workspace. Permission: gateway.view

dome_model_get

Get an LLM model connection by name. Permission: gateway.view

dome_model_add

Add an LLM model connection. Permission: gateway.manage
Add an Anthropic model

dome_model_update

Update an LLM model connection. Only provided fields change. Permission: gateway.manage Provider is immutable after create — to switch providers, add a new connection.

dome_model_remove

Remove an LLM model connection. Marked destructive. Permission: gateway.manage

dome_model_oauth_connect

Begin the shared-OAuth admin consent flow for a model configured with auth_method=oauth, credential_type=shared (Anthropic OAuth, Azure AAD service principal, Google Workload Identity for Vertex). Returns a one-shot URL valid for ~10 minutes. Permission: gateway.manage

dome_model_oauth_disconnect

Disconnect (revoke) shared-OAuth credentials for a model. Idempotent. Marked destructive. Permission: gateway.manage

Pool CRUD

Pools are logical names agents call. The gateway picks a member at request time using the pool’s routing strategy and falls back across priority buckets when a member fails.

dome_model_pool_list

List LLM pools in the active workspace. Permission: gateway.view

dome_model_pool_get

Get a pool with its members. Permission: gateway.view

dome_model_pool_create

Create an LLM pool. Permission: gateway.manage

dome_model_pool_update

Update a pool. Only provided fields change. Permission: gateway.manage

dome_model_pool_set_default

Set the workspace’s default pool. Replaces any prior default. Permission: gateway.manage

dome_model_pool_move

Reposition a pool in its workspace’s match_when evaluation order. Pools with non-empty predicates evaluate in ascending sort_key; the first match wins. Exactly one of before or after is required. Permission: gateway.manage

dome_model_pool_remove

Remove an LLM pool. Marked destructive. Permission: gateway.manage

Pool Member CRUD

Members are model connections inside a pool, each with a priority and weight. Failover walks ascending priority; within a priority bucket, requests distribute by weight.

dome_model_pool_member_list

List members of a pool. Permission: gateway.view

dome_model_pool_member_add

Add a model to a pool. Permission: gateway.manage
Add a member with failover

dome_model_pool_member_update

Update a pool member’s priority, weight, or enabled flag. Permission: gateway.manage

dome_model_pool_member_remove

Remove a model from a pool. Marked destructive. Permission: gateway.manage

Cost quotas

Cost quotas cap USD spend over a window and gate routing — total caps reject with HTTP 429 when exhausted, while per-model budgets lock a model out of routing so the pool spills to the next member. Refer to Cost quotas for the enforcement model and subjects.

dome_model_quota_list

List LLM cost quotas in the active workspace. Permission: gateway.view

dome_model_quota_set

Create a USD spend cap. The subject decides what the cap covers. Permission: gateway.manage
Per-model in-pool budget (drives spill-over)

dome_model_quota_remove

Remove a cost quota by id. Marked destructive. Permission: gateway.manage

Next steps

Add connections and pools from Connect when you want the full workflow: