Skip to content
Reference
IAM Resources
ai

ai

create-deployment 

[`POST /ai/deployment`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#create-deployment)

Create an AI Deployment

Parameters:

  • parameters.name

  • parameters.gpu_type

  • parameters.gpu_count

  • parameters.replicas

  • parameters.inference_engine_parameters

  • parameters.inference_engine_version

create-model 

[`POST /ai/model`](https://community.exoscale.com/reference/api/ai/dedicated-inference/ai-model/#create-model)

Create an AI Model

Parameters:

  • parameters.name

  • parameters.huggingface_token

delete-deployment 

[`DELETE /ai/deployment/<id>`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#delete-deployment)

Delete an AI Deployment

Parameters:

  • parameters.id

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at

delete-model 

[`DELETE /ai/model/<id>`](https://community.exoscale.com/reference/api/ai/dedicated-inference/ai-model/#delete-model)

Delete an AI Model

Parameters:

  • parameters.id

Resources:

  • resources.model.id
  • resources.model.name
  • resources.model.state
  • resources.model.model_size
  • resources.model.created_at
  • resources.model.updated_at

get-deployment 

[`GET /ai/deployment/<id>`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#get-deployment)

Get an AI Deployment

Parameters:

  • parameters.id

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at

get-deployment-logs 

[`GET /ai/deployment/<id>/logs`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#get-deployment-logs)

Get an AI Deployment logs

Parameters:

  • parameters.id

  • parameters.stream

  • parameters.tail

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at

get-inference-engine-help 

[`GET /ai/help/inference-engine-parameters`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#get-inference-engine-help)

Get Inference Engine Help

Parameters:

  • parameters.version

get-model 

[`GET /ai/model/<id>`](https://community.exoscale.com/reference/api/ai/dedicated-inference/ai-model/#get-model)

Get an AI Model

Parameters:

  • parameters.id

Resources:

  • resources.model.id
  • resources.model.name
  • resources.model.state
  • resources.model.model_size
  • resources.model.created_at
  • resources.model.updated_at

list-ai-instance-types 

[`GET /ai/instance-type`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#list-ai-instance-types)

List AI Instance Types

list-deployments 

[`GET /ai/deployment`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#list-deployments)

List AI Deployments

list-models 

[`GET /ai/model`](https://community.exoscale.com/reference/api/ai/dedicated-inference/ai-model/#list-models)

List AI Models

reveal-deployment-api-key 

[`GET /ai/deployment/<id>/api-key`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#reveal-deployment-api-key)

Reveal an AI Deployment API Key

Parameters:

  • parameters.id

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at

scale-deployment 

[`POST /ai/deployment/<id>/scale`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#scale-deployment)

Scale an AI Deployment

Parameters:

  • parameters.id

  • parameters.replicas

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at

update-deployment 

[`PATCH /ai/deployment/<id>`](https://community.exoscale.com/reference/api/ai/dedicated-inference/deployment/#update-deployment)

Update an AI Deployment

Parameters:

  • parameters.id

  • parameters.name

  • parameters.inference_engine_parameters

  • parameters.inference_engine_version

Resources:

  • resources.deployment.id
  • resources.deployment.name
  • resources.deployment.state
  • resources.deployment.gpu_type
  • resources.deployment.gpu_count
  • resources.deployment.replicas
  • resources.deployment.deployment_url
  • resources.deployment.inference_engine_version
  • resources.deployment.inference_engine_parameters
  • resources.deployment.service_level
  • resources.deployment.state_details
  • resources.deployment.created_at
  • resources.deployment.updated_at
Last updated on