Create Deployment

Add MCP server to your AI tool

Allow AI tools and LLMs to interact with the API documentation portal through MCP.

MCP server URL


        
          
            https://openapi-v2.exoscale.com/mcp

Standard setup for AI tools providing an mcp.json file

{
  "Exoscale APIv2 MCP server": {
    "url": "https://openapi-v2.exoscale.com/mcp"
  }
}

POST /ai/deployment

Deploy a model on an inference server

application/json

Body Required

gpu-count integer(int64) Required

Number of GPUs (1-8)

Minimum value is 1.
inference-engine-version string

Inference engine version

Values are 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, or 0.26.0. Default value is 0.26.0.
name string Required

Deployment name

Minimum length is 1.
gpu-type string Required

GPU type family (e.g., gpua5000, gpu3080ti)
product-name string

Billing identifier for this deployment. Used by the Router for usage counters and Kafka events.

Minimum length is 1.
replicas integer(int64) Required

Number of replicas (>=1)

Minimum value is 1.
inference-engine-parameters array[string]

Optional extra inference engine server CLI args
model object Required

Model reference. Provide either id or name.
Hide model attributes Show model attributes object
- name string
  
  Associated model name
  
  Minimum length is 1.
- id string(uuid)
  
  Associated model ID

Responses

412 application/json

412 (probably insufficient GPUs)
Hide response attributes Show response attributes object
- type string(uri-reference) Required
  
  An absolute or relative URI reference pointing to human-readable documentation concerning the specific problem type encountered.
- title string Required
  
  A brief summary defining the class of failure, optimal for quick user interface groupings.
- status integer Required
  
  Minimum value is 100, maximum value is 599.
- detail string Required
  
  A highly contextual, readable explanation breaking down explicitly what triggered this error scenario.
403 application/json

Forbidden
Hide response attributes Show response attributes object
- type string(uri-reference) Required
  
  An absolute or relative URI reference pointing to human-readable documentation concerning the specific problem type encountered.
- title string Required
  
  A brief summary defining the class of failure, optimal for quick user interface groupings.
- status integer Required
  
  Minimum value is 100, maximum value is 599.
- detail string Required
  
  A highly contextual, readable explanation breaking down explicitly what triggered this error scenario.
200 application/json

OK
Hide response attributes Show response attributes object
- id string(uuid)
  
  Operation ID
- reason string
  
  Operation failure reason
  
  Values are incorrect, unknown, unavailable, forbidden, busy, fault, partial, not-found, interrupted, unsupported, or conflict.
- reference object
  
  Related resource reference
  
  Hide reference attributes Show reference attributes object
  
  id string(uuid)
  
  Reference ID
  
  link string
  
  Link to the referenced resource
  
  command string
  
  Command name
- message string
  
  Operation message
- state string
  
  Operation status
  
  Values are failure, pending, success, or timeout.
400 application/json

Bad Request
Hide response attributes Show response attributes object
- type string(uri-reference) Required
  
  An absolute or relative URI reference pointing to human-readable documentation concerning the specific problem type encountered.
- title string Required
  
  A brief summary defining the class of failure, optimal for quick user interface groupings.
- status integer Required
  
  Minimum value is 100, maximum value is 599.
- detail string Required
  
  A highly contextual, readable explanation breaking down explicitly what triggered this error scenario.

POST /ai/deployment

curl \
 --request POST 'https://api-ch-gva-2.exoscale.com/v2/ai/deployment' \
 --header "Content-Type: application/json" \
 --data '{"gpu-count":42,"inference-engine-version":"0.26.0","name":"string","gpu-type":"string","product-name":"string","replicas":42,"inference-engine-parameters":["string"],"model":{"name":"string","id":"string"}}'

Request examples

{
  "gpu-count": 42,
  "inference-engine-version": "0.26.0",
  "name": "string",
  "gpu-type": "string",
  "product-name": "string",
  "replicas": 42,
  "inference-engine-parameters": [
    "string"
  ],
  "model": {
    "name": "string",
    "id": "string"
  }
}

Response examples (412)

{
  "type": "string",
  "title": "string",
  "status": 42,
  "detail": "string"
}

Response examples (403)

{
  "type": "string",
  "title": "string",
  "status": 42,
  "detail": "string"
}

Response examples (200)

{
  "id": "string",
  "reason": "incorrect",
  "reference": {
    "id": "string",
    "link": "string",
    "command": "string"
  },
  "message": "string",
  "state": "failure"
}

Response examples (400)

{
  "type": "string",
  "title": "string",
  "status": 42,
  "detail": "string"
}