> 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.

# Supported endpoints

> Which LLM endpoints each kind of provider connection supports in Fabric AI Gateway, and what the gateway does with each endpoint.

An LLM route can expose only the endpoints that its providers offer. Each provider connection declares its endpoints, and the gateway sends a request only to a provider that declares the endpoint you called, in the format you sent. The gateway doesn't translate between APIs, so an OpenAI-format request never reaches an Anthropic-format endpoint. This page shows which endpoints each kind of provider supports, and what the gateway does with each one.

The exact list for each provider appears in the console. When you connect a provider, **Endpoints** lists the endpoints that it offers. For the steps, see [Connect an LLM provider](/configure/connections/llm-providers).

## Endpoints by provider

| Endpoint                                             | OpenAI | Anthropic | OpenAI-compatible servers | Amazon Bedrock |
| ---------------------------------------------------- | ------ | --------- | ------------------------- | -------------- |
| `POST /v1/chat/completions`                          | Yes    | No        | Yes                       | Varies         |
| `POST /v1/responses`                                 | Yes    | No        | Varies                    | No             |
| `POST /v1/embeddings`                                | Yes    | No        | Varies                    | No             |
| `GET /v1/models`                                     | Yes    | Yes       | Yes                       | No             |
| `GET /v1/models/{model}`                             | Yes    | Varies    | Varies                    | No             |
| `POST /v1/messages`                                  | No     | Yes       | No                        | No             |
| `POST /v1/messages/count_tokens`                     | No     | Yes       | No                        | No             |
| `POST /model/{model_id}/invoke`                      | No     | No        | No                        | Yes            |
| `POST /model/{model_id}/invoke-with-response-stream` | No     | No        | No                        | Yes            |

**Varies** means it depends on the provider or on how the connection is set up. Check **Endpoints** for the connection.

To use Claude models from an OpenAI-compatible client, connect a provider whose connection declares an OpenAI-compatible chat endpoint. Otherwise, use `/v1/messages` with an Anthropic client.

## What the gateway does with each endpoint

| Endpoint family                                  | Request format     | Where the gateway reads the model       | Streaming                                   | Token usage                                                    |
| ------------------------------------------------ | ------------------ | --------------------------------------- | ------------------------------------------- | -------------------------------------------------------------- |
| OpenAI Chat Completions                          | OpenAI chat        | `model` in the JSON body                | Server-sent events, with `"stream": true`   | Read from the response                                         |
| OpenAI Responses                                 | OpenAI responses   | `model` in the JSON body                | Server-sent events, with `"stream": true`   | Read from the response                                         |
| Anthropic Messages                               | Anthropic messages | `model` in the JSON body                | Server-sent events, with `"stream": true`   | Read from the response                                         |
| Embeddings and other OpenAI-compatible endpoints | Passed through     | `model` in the JSON body, where present | As the provider sends it                    | Read from the response in the provider's format, where present |
| `GET /v1/models`                                 | No body            | None                                    | None                                        | None                                                           |
| Bedrock InvokeModel                              | Anthropic messages | The `{model_id}` path segment           | AWS event stream, on the streaming endpoint | Read from the response                                         |

Notes:

* **Model checks.** If a connection allows only some models, the gateway checks the model on every endpoint that names one. A request whose model the gateway can't read on such an endpoint is refused. For the errors, see [Gateway error codes](/reference/error-codes#400-model-not-allowed).
* **OpenAI chat streams.** OpenAI includes token usage in a chat stream only when the request sets `stream_options.include_usage` to `true`. The gateway doesn't add it for you, so without it a streamed chat request records no tokens.
* **Token counting.** The gateway records token usage only when your organization has LLM observability turned on. For details, see [Monitor gateway traffic](/use/monitor).

## Routes with several providers

A route can have several provider connections. On such a route:

* A routing plugin, such as the LLM Router, chooses which connections to try and in what order. Without one, the request must name a connection in the `x-gateway-service` header.
* The gateway accepts the request if any connection on the route declares the endpoint.
* Each fallback attempt uses its own connection's endpoint and credentials, and skips connections that don't declare the endpoint or don't allow the model.
* All connections that declare the same path on a route must use the same API format. Fabric refuses to save a route that mixes them.

On a route with the `llm-model-router` plugin, `GET /v1/models` and `GET /v1/models/{model}` are answered by the gateway from the models that the route's connections allow, not by a provider. For details, see [Route requests by model name](/configure/routing/model-router).

## Next steps

* Connect a provider by following [Connect an LLM provider](/configure/connections/llm-providers).
* Send requests to the endpoints in [Gateway API reference](/reference/gateway-api).
* Set up failover between providers in [Fail over across providers with the LLM Router](/configure/routing/failover).