Skip to main content
Two policies shape the request itself before it is forwarded. Both run at pre_request and are scoped like any other policy.

​
model_allowlist

Restrict which models a consumer or gateway may call, matching by name with glob patterns. This is the policy-based complement to a consumer’s model_policies — use it for a gateway-wide default.
SettingTypeDefaultNotes
allowed_modelsstring[]—Name patterns permitted, * wildcard (e.g. gpt-5*). Required.
behavior_on_disallowedenumrejectreject (403) or substitute.
substitute_withstring—Model written back when substitute (must match the allowlist).
default_modelstring—Model injected when the request omits one (must match the allowlist).
{
  "slug": "model_allowlist",
  "settings": {
    "allowed_models": ["gpt-4o", "gpt-4o-mini"],
    "behavior_on_disallowed": "substitute",
    "substitute_with": "gpt-4o-mini"
  }
}

​
prompt_template

Inject and version prompts server-side, so system instructions live in the gateway rather than in every client. It supports two modes, which can be combined:
  • Mode A — inject templates: render operator-defined system prompts from context variables (headers or JWT claims) and inject them into the request.
  • Mode B — named templates: maintain named, versioned templates that clients reference by {template://name@label}, with required-variable validation.
SettingTypeDefaultNotes
template_engineenummustacheRendering engine (mustache in v1).
context_variablesmap—Named values resolved from header or jwt_claim sources.
inject_templatesarray—Mode A: [{ id, content, position, on_existing_system }].
named_templatesarray—Mode B: named templates with versions[] (each { version, labels, content, required_variables }).
allow_untemplated_requestsbooltrueWhen false + named templates set, reject requests with no template reference.
on_missing_context_variableenumerrorerror, empty_string, or skip_injection.
default_labelstring—Label used when a reference omits @label.
{
  "slug": "prompt_template",
  "settings": {
    "context_variables": {
      "tenant": { "source": "header", "name": "X-Tenant-Id" }
    },
    "inject_templates": [
      { "id": "base", "content": "You are the assistant for {{tenant}}.", "on_existing_system": "merge" }
    ]
  }
}
Injected content is placed in the system role; on_existing_system chooses whether to merge with or replace an existing system prompt.