---
title: "Observe Async Chat Stream Events"
method: GET
path: "/v1/messages/async/{message_id}/stream"
tags: ["Async Messages"]
---

# Observe Async Chat Stream Events

`GET /v1/messages/async/{message_id}/stream`

Observe an asynchronous chat stream via Server-Sent Events.

This endpoint provides a Server-Sent Events stream that delivers
chat completion events in real-time. The events follow
the same format as synchronous chat streaming responses.

Stream Lifecycle:
1. Stream initiated via POST /v1/messages/async
2. Events begin flowing when processing starts
3. Stream automatically closes when message completes
4. Stream can be cancelled via POST /v1/messages/async/{message_id}/cancel

Notes:
* Stream remains active until message completion or cancellation
* Events are delivered in chronological order
* Connection will automatically close when stream ends
* Use appropriate SSE client libraries for robust event handling

## Path parameters

- `message_id` string, required — Message ID of the asynchronous chat stream to observe.

## Response `200`

Server-sent events stream with chat completion data

- unknown

## Other responses

- `401` — Unauthorized
- `404` — Stream not found
- `422` — Validation Error

## Changes

- **2026-06-02** `c711b911f68e` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/zylon-ai/apis/private-gpt-api/changes/v1/messages/async/:message_id/stream/get.md)

---

[API](https://skmtc.dev/zylon-ai/apis/private-gpt-api.md) · [All operations](https://skmtc.dev/zylon-ai/apis/private-gpt-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/zylon-ai/private-gpt-api/revisions/4e828cf153c4/schema)