---
title: "Deploy a model"
method: POST
path: "/v1/deploy"
tags: ["Deployments"]
---

# Deploy a model

`POST /v1/deploy`

## Request

- Base URL: `https://api.auxen.ai`
- URL: `https://api.auxen.ai/v1/deploy`
- Auth: HTTP bearer

Returns immediately with `status: deploying`. Poll `GET /v1/deployments/{deploymentId}` until `status: ready`, then use the returned `endpoint` + `api_key` for inference.

## Request body

- object
  - `model` string, required: Model ID from GET /v1/models
  - `throughput` union: Throughput level. More throughput handles more simultaneous requests at the same answer quality. Double, Quad, and Max cost 1.9×, 3.75×, and 7.5× the Standard rate. Numbers 1/2/4/8 are accepted as aliases.
    - 'standard' | 'double' | 'quad' | 'max'
    - 1 | 2 | 4 | 8
  - `capacity` 1 | 2 | 4 | 8: Deprecated alias of `throughput`; returned until 2027-04-02.
  - `billing` 'pay_as_you_go' | 'on_demand': Optional. `on_demand` is a back-compat alias for `pay_as_you_go`.
  - `label` string
  - `webhook_url` string, uri: URL Auxen POSTs this deployment's lifecycle events to.

## Response `202`

Accepted — deployment started.

- object
  - `success` true, required
  - `data` object, required
    - `deployment_id` string
    - `instance_id` string: Deprecated alias of `deployment_id`; returned until 2027-04-02.
    - `status` 'deploying'
    - `legacy_status` 'provisioning'
    - `model` string
    - `billing` 'pay_as_you_go'
    - `throughput` 'standard' | 'double' | 'quad' | 'max'
    - `throughput_multiplier` 1 | 2 | 4 | 8
    - `capacity` integer: Deprecated alias of `throughput_multiplier`; returned until 2027-04-02.
    - `rate_per_hour` string
    - `hourly_rate` number: Deprecated alias of `rate_per_hour`; returned until 2027-04-02.
    - `ready_estimate` string, date-time
    - `estimated_ready_at` string, date-time: Deprecated alias of `ready_estimate`; returned until 2027-04-02.
    - `polling_url` string, uri
  - `meta` Meta, required
    - `requestId` string
    - `timestamp` string, date-time

## Other responses

- `400`: Validation failure (missing model, bad throughput).
- `402`: Insufficient credits.

---

[API](https://skmtc.dev/auxen/apis/auxen-headless-api.md) · [All operations](https://skmtc.dev/auxen/apis/auxen-headless-api/llms.txt) · [OpenAPI document](https://skmtc.dev/auxen/apis/auxen-headless-api/revisions/164be65f5ce8?raw)