---
title: "Signal the LLM to finish its response gracefully."
method: POST
path: "/messages/{question_id}/finish"
tags: ["Chat"]
---

# Signal the LLM to finish its response gracefully.

`POST /messages/{question_id}/finish`

## Request

- Base URL: `https://h2ogpte.genai.h2o.ai/api/v1`
- URL: `https://h2ogpte.genai.h2o.ai/api/v1/messages/{question_id}/finish`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/h2o/apis/h2ogpte-rest-api/docs/messages/:question_id/finish/post.ts> (a function with typed inputs; its response is checked against the schema)

Signals the LLM to complete its current thought and finish naturally, providing a more coherent ending than an immediate stop.

## Path parameters

- `question_id` string, required

## Response `204`

Successful operation

## Other responses

- `400`: Bad request
- `401`: Unauthorized - Invalid or missing API key
- `default`: Unexpected error

---

[API](https://skmtc.dev/h2o/apis/h2ogpte-rest-api.md) - [All operations](https://skmtc.dev/h2o/apis/h2ogpte-rest-api/llms.txt) - [OpenAPI document](https://skmtc.dev/h2o/apis/h2ogpte-rest-api/revisions/a82a117320f4?raw)