> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gloo.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Endpoint Types

> Guarded, direct, and grounded — the three endpoint families on Gloo AI, what each one runs around your request, and how to choose between them.

Every Gloo AI inference endpoint belongs to one of three families. All three share the same model catalog, authentication, metering and rate limits. What differs is **what runs around your request**.

| Family       | What Gloo adds                                           | Endpoints                                                       |
| :----------- | :------------------------------------------------------- | :-------------------------------------------------------------- |
| **Guarded**  | Guardrails, output moderation, values-alignment, routing | `/ai/v2/guarded/responses`, `/ai/v2/guarded/chat/completions`   |
| **Direct**   | Nothing between your prompt and the provider             | `/ai/v2/direct/responses`, `/ai/v2/direct/chat/completions`     |
| **Grounded** | Retrieval over your own uploaded content (RAG)           | `/ai/v1/grounded/responses`, `/ai/v2/grounded/chat/completions` |

Each family comes in both request shapes — the OpenAI-compatible **Responses** format and the **Chat Completions** format — so the family and the shape are independent choices.

## Guarded endpoints

The recommended default, and where new integrations should start. A guarded request runs Gloo's full safety and values pipeline: input guardrails, output moderation, values-aligned (`tradition`) responses, `model_family` selection and intelligent auto-routing across models.

* [Responses](/api-guides/responses) (`POST /ai/v2/guarded/responses`) — the recommended surface for new work.
* [Completions](/api-guides/completions-v2) (`POST /ai/v2/guarded/chat/completions`) — fully supported, and the home of routing and `model_family`.

## Direct endpoints

Direct endpoints send your request straight to the model you name. Gloo adds nothing between your prompt and the provider: no guardrails, no output moderation, no values-alignment, no routing. What you send is what the model sees; what the model returns is what you get. You can spot a direct endpoint by the `/direct/` segment in its path.

Use them when your application owns its own safety and prompting end to end — an agent framework with its own moderation, a backend that composes prompts itself, tooling that needs byte-faithful model behavior.

* [Direct Responses](/api-guides/direct-responses) (`POST /ai/v2/direct/responses`) — for new work that owns its own safety; multimodal.
* [Direct Completions](/api-guides/direct-completions) (`POST /ai/v2/direct/chat/completions`) — for existing Chat Completions tooling.

### What runs, and what does not

Direct means direct about *content*, not a bypass of the platform:

**Still applies on every direct request:**

* Authentication (Bearer API key) and organization entitlement
* Usage metering and billing
* The Gloo model catalog — you address models by their `gloo-*` Model ID
* **Provider resiliency.** Gloo serves the model you asked for, but not always from the same place: when the provider currently serving it is failing or unhealthy, your request fails over to another provider that serves the same model, and a stream cut mid-answer can be continued on a fallback provider. The `model` you receive is the `model` you asked for — resiliency changes who serves it, never what you get.
* Platform rate limits

**Deliberately not applied:**

* Input guardrails and output moderation
* Values-alignment (`tradition`)
* `model_family` selection and intelligent auto-routing — nothing picks a *different model* than the one you named (distinct from provider resiliency above, which only changes which provider serves that same model)
* Gloo prompt augmentation — your messages go to the model verbatim

<Warning>
  On direct endpoints, safety is your application's responsibility. Nothing screens the input before the model sees it, and nothing reviews the output before your user does. If any part of your traffic needs screening, route it through the guarded [Responses](/api-guides/responses) or [Completions](/api-guides/completions-v2) endpoints.
</Warning>

## Grounded endpoints

Grounded endpoints retrieve relevant passages from content you have uploaded, inject them as context before generation, and tell you whether the answer was grounded in your sources.

* [Grounded Responses](/api-guides/grounded-responses) (`POST /ai/v1/grounded/responses`) — grounding in the Responses shape.
* [Grounded Completions](/api-guides/grounded-completions) (`POST /ai/v2/grounded/chat/completions`) — grounding on Completions V2, with citation metadata and `tradition`.

## Which endpoint should I use?

| Use case                                                              | Recommended endpoint                                                            |
| :-------------------------------------------------------------------- | :------------------------------------------------------------------------------ |
| New integration with OpenAI-compatible tooling                        | [Responses](/api-guides/responses) — the guarded default                        |
| Guardrails, output moderation, values-aligned (`tradition`) responses | [Responses](/api-guides/responses) or [Completions](/api-guides/completions-v2) |
| Your application owns its own safety and prompting                    | [Direct Responses](/api-guides/direct-responses)                                |
| Byte-faithful model behavior, nothing added to the prompt             | [Direct Responses](/api-guides/direct-responses)                                |
| Existing Chat Completions tooling that should keep its request shape  | [Direct Completions](/api-guides/direct-completions)                            |
| Vision (image input) or image generation                              | Either Responses endpoint — same request shape                                  |
| Grounded / RAG answers over your own content                          | [Grounded Responses](/api-guides/grounded-responses)                            |
| Grounding with citation metadata or `tradition`                       | [Grounded Completions](/api-guides/grounded-completions)                        |
| Intelligent auto-routing across models                                | [Completions](/api-guides/completions-v2)                                       |

When in doubt, start with the guarded [Responses](/api-guides/responses) API. The guarded and direct Responses endpoints take the same request body, so moving between them later is a URL change.

## Legacy endpoint aliases

The previous v2 paths remain available as aliases for existing integrations. New integrations should use the canonical paths above:

| Previous path                      | Canonical path                     |
| :--------------------------------- | :--------------------------------- |
| `/ai/v2/chat/completions`          | `/ai/v2/guarded/chat/completions`  |
| `/ai/v2/chat/completions/grounded` | `/ai/v2/grounded/chat/completions` |
| `/ai/v2/responses`                 | `/ai/v2/guarded/responses`         |

The `/ai/v1/grounded/responses` endpoint is unchanged.