---
title: "Get Deployment"
method: GET
path: "/ai/deployment/{id}"
tags: ["deployment"]
---

# Get Deployment

`GET /ai/deployment/{id}`

## Request

- Base URL: `https://api-ch-gva-2.exoscale.com/v2`
- URL: `https://api-ch-gva-2.exoscale.com/v2/ai/deployment/{id}`
- Auth: none declared
- TypeScript: <https://skmtc.dev/exoscale/apis/exoscale-api/docs/ai/deployment/:id/get.ts> (a function with typed inputs; its response is checked against the schema)

Get Deployment details

## Path parameters

- `id` string, uuid, required

## Response `200`

OK

- GetDeploymentResponse: AI deployment
  - `gpu-count` integer: Number of GPUs
  - `updated-at` string, date-time: Update time
  - `deployment-url` string, required: Deployment inference endpoint URL
  - `service-level` string: Service level
  - `inference-engine-version` '0.12.0' | '0.15.1' | '0.16.0' | '0.17.0' | '0.18.0' | '0.18.1' | '0.19.0' | '0.19.1' | '0.20.0' | '0.20.1' | '0.20.2' | '0.21.0' | '0.22.0' | '0.22.1' | '0.23.0' | '0.24.0' | '0.25.0' | '0.25.1' | '0.26.0': Inference engine version
  - `name` string, required: Deployment name
  - `state` 'ready' | 'creating' | 'preparing' | 'error' | 'deploying' | 'scaling' | 'updating', required: Deployment state
  - `gpu-type` string: GPU type family
  - `id` string, uuid: Deployment ID
  - `replicas` integer: Number of replicas (>=0)
  - `state-details` string: Deployment state details
  - `created-at` string, date-time: Creation time
  - `visibility` 'public' | 'private', required: Deployment visibility: private for your organization's deployments, public for Exoscale Managed Inference deployments.
  - `inference-engine-parameters` string[]: Optional extra inference engine server CLI args
  - `model` ModelRef, required: Model reference. Provide either id or name.
    - `name` string: Associated model name
    - `id` string, uuid: Associated model ID

## Other responses

- `404`: Not Found

## Changes

- **2026-11-06** `63da6f74c845`: 20 warning, 6 info
  - removed the optional property `errors` from the response with the `404` status
  - removed the optional property `instance` from the response with the `404` status
  - added the new `0.18.0` enum value to the `inference-engine-version` response property for the response status `200`
  - added the new `0.18.1` enum value to the `inference-engine-version` response property for the response status `200`
  - …22 more
- **2026-03-16** `e05707a7b346`: 2 warning, 12 info
  - removed the optional property `error` from the response with the `404` status
  - removed the optional property `status` from the response with the `200` status
  - api tag `deployment` added
  - api tag `dedicated-inference` removed
  - …10 more
- **2025-11-14** `352cae63dff6`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/exoscale/apis/exoscale-api/changes/ai/deployment/:id/get.md)

---

[API](https://skmtc.dev/exoscale/apis/exoscale-api.md) - [All operations](https://skmtc.dev/exoscale/apis/exoscale-api/llms.txt) - [OpenAPI document](https://skmtc.dev/exoscale/apis/exoscale-api/revisions/63da6f74c845?raw)