ZuploZuplo
LoginStart for Free
  • Documentation
  • API Reference
Introduction
Getting Started
    Develop in the portal
      1 - Setup Your Gateway2 - Rate Limiting3 - API Key Auth4 - Deploy5 - Dynamic Rate LimitingDynamic MCP Server - Quickstart
    Develop locally with the CLI
      1 - Setup Your Gateway2 - Rate Limiting3 - API Key Auth4 - Deploy5 - Dynamic Rate LimitingDynamic MCP Server - Quickstart
Concepts
Development
Policies
Handlers
API Keys
Rate Limiting
Caching
MCP Server
MCP Gateway
AI Gateway
    IntroductionGetting StartedSource ControlUniversal API
    Providers
    Teams
    Apps
    Policies
      OverviewAPI key authenticationModel FilteringFallback ModelBudgets and CostsSemantic cacheAkamai AI FirewallComet Opik tracingGalileo tracing
    Cookbooks
    Integrations
Developer Portal
Monetization
GraphQL
Deploying & Source Control
Analytics
Observability
Networking & Infrastructure
Account Management
Programming API
Build with AI
Zuplo CLI
Migration Guides
Platform LimitsVersion Support PolicySecuritySupportTrust & ComplianceChangelog
powered by Zudoku
Policies

Model Filtering

ai-gateway-model-filtering-v2

Model Filtering decides which models an app may use and creates the model selection the rest of the chain works from. Without it, an app can reach any model offered by the providers assigned to its team.

Configure each capability—completions, embeddings—in one of two modes. The modes are mutually exclusive per capability.

  • An allow list exposes a curated set of models. The first entry is the default when a request names no model.
  • A block list permits every available model except the ones named. Each request must name its model, because a block list supplies no default.

Models are written as providerName/model, where providerName is the provider name configured in your gateway—for example openai/gpt-5.

What a rejected request gets

RequestResponse
A model the rules don't allow403, listing what's allowed
No model named, in block list mode400
A capability the policy doesn't configure at all403
A provider name that isn't in the catalog400

Rejections are returned as problem details, and the detail names what the caller should have sent—the allowed models for a blocked model, or the gateway's configured provider names for an unrecognized one. The Akamai AI Firewall is the exception among the policies here: it answers in the provider's own error format instead.

Place Model Filtering first in the chain—it creates the model selection that Fallback Model and Budgets and Costs build on.

For the portal workflow see Restricting models; for every option see the generated reference. When model selection needs logic instead of a list, see Dynamic model routing.

Edit this page
Last modified on August 5, 2026
API key authenticationFallback Model
On this page
  • What a rejected request gets