---
title: "Evaluate Request"
method: POST
path: "/detection/v2/request-evaluations"
tags: ["interactions-v2_other"]
---

# Evaluate Request

`POST /detection/v2/request-evaluations`

[BETA] This endpoint is not GA or Production ready and is subject to changes at any time. Breaking changes may occur.

Analyzes an LLM request payload for security threats before it is sent to the model.

Accepts any valid provider request payload and returns:
- If detect or redact action: the request payload (potentially modified) in the provider's request format
- If block action: a canned block message in the provider's response format

Use this endpoint inline in your LLM pipeline to evaluate prompts before they reach the model.

Supported provider formats:
- [OpenAI Chat Completions](https://platform.openai.com/docs/api-reference/chat)
- [OpenAI Responses](https://platform.openai.com/docs/api-reference/responses)
- [Anthropic Messages](https://docs.anthropic.com/en/api/messages)

## Headers

- `HL-Project-Id` string
- `HL-Runtime-Session-Id` string

## Request body

- ProviderPayload — A pass-through payload in the native format of the LLM provider. Any valid provider request or response payload is accepted as-is and returned in the same format.

## Response `200`

Successful evaluation. Returns the (potentially modified) provider request payload, or if a block action
was taken, a provider response payload.

- ProviderPayload — A pass-through payload in the native format of the LLM provider. Any valid provider request or response payload is accepted as-is and returned in the same format.

---

[API](https://skmtc.net/hiddenlayerai/apis/hiddenlayer-audit-api.md) · [All operations](https://skmtc.net/hiddenlayerai/apis/hiddenlayer-audit-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/hiddenlayerai/hiddenlayer-audit-api/revisions/d8c55b669109/schema)