---
title: "Asynchronously call the development deployment of a model."
method: POST
path: "/development/async_predict"
tags: ["Non-Regional"]
---

# Asynchronously call the development deployment of a model.

`POST /development/async_predict`

## Request body

- AsyncPredictRequest
  - `model_input` object, required — JSON-serializable model input.
  - `webhook_endpoint` string, uri — HTTPS URL to receive the prediction result via webhook. Both HTTP/2 and HTTP/1.1 are supported. If omitted, the model must save outputs so they can be accessed later.
  - `priority` integer — Priority of the request. Lower values are higher priority.
  - `max_time_in_queue_seconds` integer — Maximum time in seconds a request will spend in the queue before expiring. Must be between 10 seconds and 72 hours.
  - `inference_retry_config` InferenceRetryConfig — Exponential backoff parameters for retrying predict requests.
    - `max_attempts` integer — Number of predict request attempts.
    - `initial_delay_ms` integer — Minimum time between retries in milliseconds.
    - `max_delay_ms` integer — Maximum time between retries in milliseconds.

## Response `201`

Async predict request enqueued.

- object
  - `request_id` string, required — The ID of the async request.

## Other responses

- `400` — Error response.
- `401` — Error response.
- `413` — Error response.
- `429` — Error response.
- `503` — Error response.

---

[API](https://skmtc.net/baseten/apis/baseten-inference-api.md) · [All operations](https://skmtc.net/baseten/apis/baseten-inference-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/baseten/baseten-inference-api/revisions/a55a2f64c3c5/schema)