---
title: "Send a chat message"
description: "Send a natural language message to the LLM chat backend for a specific workflow.\nThe request includes the current workflow state and optional conversation history\nso the LLM can generate contextually relevant responses.\n\nThe LLM response may contain plain text explanations and/or DSL commands\nin ```flowdrop fenced code blocks. The frontend extracts and previews\nthese commands before execution.\n"
source: https://flowdrop.io/docs/api/chat/sendChatMessage
site: FlowDrop documentation
---
# Send a chat message
`POST /workflows/{id}/chat/messages`

Send a natural language message to the LLM chat backend for a specific workflow.
The request includes the current workflow state and optional conversation history
so the LLM can generate contextually relevant responses.

The LLM response may contain plain text explanations and/or DSL commands
in ```flowdrop fenced code blocks. The frontend extracts and previews
these commands before execution.

## Parameters

- `id` · in path · string · required — Workflow ID

## Request body

- `application/json` — ChatRequest

## Responses

- `200` — Chat response with LLM-generated content (`application/json`: ChatMessagesResponse)
- `400` — Bad request - invalid parameters or request body (`application/json`: ErrorResponse)
- `404` — Resource not found (`application/json`: ErrorResponse)
- `500` — Internal server error (`application/json`: ErrorResponse)

*Tags: Chat*