> 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.

# Choose a routing approach

> Compare the model router, the LLM Router, and the Adaptive Model Router, and pick the one that fits a route.

Fabric AI Gateway has three plugins that decide where an LLM request goes. They answer different questions: which provider serves the model the client named, what happens when a provider fails, and which model a request needs. This topic compares them so you can pick one for each route.

## Compare the plugins

|                            | Model router (`llm-model-router`)                                                                                        | LLM Router                                                  | Adaptive Model Router                                              |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------- | ------------------------------------------------------------------ |
| **Who picks the model**    | The client, by name, for example `openai/gpt-5.5` or an alias                                                            | The client                                                  | The plugin, based on how difficult the request is                  |
| **Providers on one route** | Several. The client reaches any of them through one base URL.                                                            | Several, all serving the models the client asks for         | One provider per request. It chooses among that provider's models. |
| **Failover**               | Per provider group, in order (`fallback`) or by weight (`loadbalance`). An alias can also fall back to another provider. | Across the connections you list, in priority order          | No failover                                                        |
| **Model list for clients** | `GET /v1/models` lists every model and alias the caller can use                                                          | No                                                          | No                                                                 |
| **Gateway key**            | `fg-api-key`, or the header each SDK already sends (`Authorization: Bearer` or `x-api-key`)                              | `fg-api-key`                                                | `fg-api-key`                                                       |
| **Set up in the console**  | **Edit as JSON** on the plugin instance                                                                                  | A form                                                      | A form                                                             |
| **Use it when**            | You want one base URL for many providers and models, the way hosted LLM routers work                                     | You want a route to keep answering during a provider outage | You want to cut cost by sending simple requests to smaller models  |

## Model router

The model router lets the client choose both the provider and the model in the `model` field. You group the route's connections by provider, and each connection serves the models you allowed on it. Clients can list what's available with `GET /v1/models`, and an alias lets them use a plain name such as `claude-sonnet-5-5` that you can point at different providers later. For the steps, see [Route requests by model name](/configure/routing/model-router).

The model router doesn't translate between APIs. A model answers only on the endpoints its provider serves, so an Anthropic model works on `/v1/messages`, and on `/v1/chat/completions` only if that provider also offers an OpenAI-compatible endpoint.

## LLM Router

The LLM Router keeps the client's model name as it is and decides which of the route's connections handles the request. Use it to fail over to a second provider that serves the same models. For the steps, see [Fail over across providers with the LLM Router](/configure/routing/failover). The LLM Router also has a Lightyear mode, which sends requests through the Lightyear service. For details, see [Route requests through Lightyear](/configure/routing/lightyear).

## Adaptive Model Router

The Adaptive Model Router replaces the model the client asked for with one that fits the request. It asks a decision service to rate each prompt, and then picks a smaller or larger model from the same provider. For the steps, see [Route requests with the Adaptive Model Router](/configure/routing/adaptive-routing).

## Use one routing plugin per route

Each of these plugins builds the list of connections that a request tries, so a route can use only one of them. Fabric refuses to save a model router on a route that already has an LLM Router or an Adaptive Model Router, and the reverse.

The model router covers most of what the LLM Router does: each provider group has its own `fallback` or `loadbalance` strategy, and an alias can fall back across providers. If you need both a choice of model and failover, use the model router.

Fabric doesn't refuse an LLM Router and an Adaptive Model Router on the same route, but requests on that route then fail with `503`. Use only one of them on a route.

## Next steps

* [Route requests by model name](/configure/routing/model-router)
* [Define model aliases](/configure/routing/aliases)
* [Choose a model](/use/llm/choose-a-model)