Proxy policy

The Proxy policy page decides what an app may ask a provider for. A new app may use every provider you have, every path and every priced model. Narrow it here when an app should be able to do less.

Provider access

The Provider access card has one switch, Configure individually.

• Off: every provider you have configured is allowed, and any provider, path or model you add later is available to this app automatically. The card lists the slugs of your providers; a disabled provider is struck through.
• On: the app may use only the providers you switch on below, and each one can be restricted further. A provider you add later is not allowed until you switch it on here.

With the switch on, one card appears per provider. Its title is the provider's name, and its description shows the URL segment clients use, /proxy/<slug>/…, and a hint about that provider's paths.

Allowed paths

Leave the list empty to allow every path the provider has. Add one or more paths to allow only those. A path is the provider's own API path without a leading slash, for example v1/responses or v1/messages. Paths are matched exactly, except that {model} in a path matches one segment, which is how Gemini's v1beta/models/{model}:generateContent names its model in the URL.

Each row has two optional settings:

• Fixed model applies to routes with no model in the body, such as transcription, and is used for pricing and the model allowlist. It is never injected into the request.
• Output cap style tells the gateway which body field carries the output limit for this path when it applies Max output tokens. Leave it on auto unless the route needs an exception. The styles are responses, chat_completions, gemini_native, anthropic and none.

A request for a path not in the list answers 403 path_not_allowed.

Allowed models

Leave the list empty to allow every model that has a price. Add model names to allow only those. Rewrites are applied before this check, so the client name is what you list here. A request for another model answers 403 model_not_allowed.

Model names are the provider's own, on every route: gemini-2.5-flash, never google/gemini-2.5-flash. OpenRouter is the exception, where the model name includes its author prefix, as OpenRouter itself names it.

Max output tokens

Empty means unrestricted. When set, a request that asks for more output than this is refused with 403 max_output_tokens_exceeded, and a request that does not name an output limit gets this value injected. Transcription routes ignore the cap.

Model rewrites

The Model rewrites card maps a model name the client sends to the model the provider receives. The rewrite is applied after the allowlist check, so the target does not need to be in Allowed models, and usage records the rewritten model.

A rewrite is how you move an app to a newer model without a release: the app keeps asking for gpt-5.6-terra and you point that name at gpt-5.6. For a bigger change, such as a different provider or fixed parameters, use a named endpoint.

Rewrite targets are checked against the price catalog, not against your providers, so they can be saved before the provider exists.

When a provider is missing

An app may name a provider you have since deleted or never added. The app's pages show a banner naming the missing providers, requests to that slug answer 502 provider_not_configured (or 502 provider_disabled for a paused one), and every other provider keeps working. With Configure individually on, the card for a missing slug says no instance answers for it, and you can turn it off or recreate the provider.

In the configuration

"routing": {
  "providers": {
    "mode": "selected",
    "selected": {
      "openai": {
        "allowed_paths": [
          "v1/responses",
          { "path": "v1/audio/transcriptions", "fixed_model": "gpt-4o-mini-transcribe", "clamp": "none" }
        ],
        "allowed_models": ["gpt-5.6", "gpt-5.6-terra"],
        "max_output_tokens": 4096
      },
      "anthropic": { "allowed_paths": [], "allowed_models": [] }
    }
  },
  "model_rewrites": { "gpt-5.6-terra": "gpt-5.6" }
}

mode is all or selected. With selected, the keys of selected are provider slugs, and a slug not listed is not allowed. An entry with empty lists allows every path and every priced model of that provider. When you create an app, every slug you name must exist; when you update one, only slugs the update introduces are checked, so removing a provider never blocks unrelated edits.