> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.fabricgateway.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.fabricgateway.ai/_mcp/server.

# Configure the gateway

> Find the right topic for connecting providers, routing and securing traffic, monitoring requests, and managing access in Fabric AI Gateway.

You configure Fabric AI Gateway in the console, or with the admin API. The topics are grouped by what you want to do, in roughly the order that a first setup follows. If you haven't used the console yet, start with [Explore the console](/get-started/console).

## Connect and route

#### [Connections](/configure/connections)

Connect and manage LLM providers, MCP servers, and REST APIs, and review the routes that expose them.

#### [Providers](/configure/providers/openai)

Set up OpenAI, Anthropic, Amazon Bedrock, Azure OpenAI, Google Gemini, or a self-hosted model as an LLM provider.

#### [Credentials](/configure/credentials)

Manage the credentials that the gateway uses, and understand where secrets are stored on cloud and enterprise tenants.

#### [LLM routing](/configure/routing)

Compare the routing plugins that choose a model for each LLM request or fail over across providers.

## Govern and secure

#### [Key Auth](/configure/authentication/key-auth)

Require a gateway key on a route, choose the header that carries it, and troubleshoot authentication errors.

#### [JWT Auth](/configure/authentication/jwt-auth)

Authenticate callers with JSON Web Tokens from your identity provider, and use token claims to control which tools an agent can use.

#### [Model access](/configure/access-and-limits/model-access)

Limit which models a connection serves, and which users can use a connection and its tools.

#### [Rate limits](/configure/access-and-limits/rate-limits)

Cap how many requests or LLM tokens a caller can use in a time window, and what clients get when they reach the limit.

#### [Budgets](/configure/access-and-limits/budgets)

Set a spending budget for your organization or a namespace, adjust costs for your provider discounts, cap what you pay Fabric, and cap token use per caller.

#### [Plugins](/configure/plugins)

Secure, transform, observe, and control the cost of LLM, MCP, and HTTP API traffic with plugins.

## Administer your organization

#### [Admin](/configure/organization)

Understand the roles that control access to your organization and its namespaces, how cloud and enterprise tenants differ, and where to review activity and billing.

## Manage with the API

#### [Admin API](/configure/automation/admin-api)

Call the Fabric AI Gateway admin API with an API key to create connections, routes, and plugin instances from scripts and pipelines.

#### [API keys](/configure/automation/api-keys)

Create admin API keys to manage your Fabric AI Gateway organization programmatically.