AgentGateway · Schema

LLMBackend

Configuration for an LLM provider backend in AgentGateway, defining the target model, authentication, and routing parameters.

AI GatewayAPI GatewayMCPLLMAgent-to-AgentOpen-SourceCNCFObservabilitySecurity

Properties

Name Type Description
name string Unique name for this LLM backend.
provider string The LLM provider for this backend.
model string The model identifier to use for requests.
alias string Optional alias exposed to clients instead of the actual model name.
baseUrl string Base URL for the LLM provider API endpoint.
authentication object Authentication configuration for this backend.
weight integer Load balancing weight for this backend (higher means more traffic).
priority integer Failover priority, lower values have higher priority.
View JSON Schema on GitHub

JSON Schema

agentgateway-llm-backend-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/json-schema/agentgateway-llm-backend-schema.json",
  "title": "LLMBackend",
  "description": "Configuration for an LLM provider backend in AgentGateway, defining the target model, authentication, and routing parameters.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Unique name for this LLM backend.",
      "example": "openai-gpt4"
    },
    "provider": {
      "type": "string",
      "description": "The LLM provider for this backend.",
      "enum": ["openai", "anthropic", "gemini", "bedrock", "azure-openai", "ollama", "vllm"],
      "example": "openai"
    },
    "model": {
      "type": "string",
      "description": "The model identifier to use for requests.",
      "example": "gpt-4o"
    },
    "alias": {
      "type": "string",
      "description": "Optional alias exposed to clients instead of the actual model name.",
      "example": "primary-llm"
    },
    "baseUrl": {
      "type": "string",
      "format": "uri",
      "description": "Base URL for the LLM provider API endpoint.",
      "example": "https://api.openai.com/v1"
    },
    "authentication": {
      "type": "object",
      "description": "Authentication configuration for this backend.",
      "properties": {
        "type": {
          "type": "string",
          "enum": ["bearer", "apikey", "basic"],
          "example": "bearer"
        },
        "secretRef": {
          "type": "string",
          "description": "Reference to a secret containing the API key.",
          "example": "openai-api-key"
        }
      }
    },
    "weight": {
      "type": "integer",
      "description": "Load balancing weight for this backend (higher means more traffic).",
      "example": 100
    },
    "priority": {
      "type": "integer",
      "description": "Failover priority, lower values have higher priority.",
      "example": 1
    }
  },
  "required": ["name", "provider", "model"]
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/agentgateway-llm-backend"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.