GET
/
v2
/
deployments
curl -X GET \
  "https://api.adaline.ai/v2/deployments?promptId=prompt_123&deploymentId=deploy_456" \
  -H "Authorization: Bearer your_workspace_api_key" \
  -H "Content-Type: application/json"


{
  "id": "deploy_456",
  "createdAt": 1704067200000,
  "updatedAt": 1704067200000,
  "createdByUserId": "user_789",
  "updatedByUserId": "user_789",
  "projectId": "project_abc",
  "promptId": "prompt_123",
  "deploymentEnvironmentId": "env_123",
  "prompt": {
    "config": {
      "model": "gpt-4o-mini",
      "providerName": "openai",
      "providerId": "6e94350a-95a9-48e7-8eab-a9f35ec2dc9d",
      "settings": {
        "temperature": 0.7,
        "maxTokens": 1000,
        "topP": 1,
        "frequencyPenalty": 0,
        "presencePenalty": 0
      }
    },
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "{{user_input}}"
      }
    ],
    "tools": [],
    "variables": [
      {
        "name": "user_input",
        "description": "The user's input",
        "content": {
          "modality": "text",
          "value": "Who wrote the book 'The Great Gatsby'?"
        }
      }
    ]
  }
}
​
header
string

All requests require a valid workspace API key passed in the Authorization header:

Authorization: Bearer YOUR_WORKSPACE_API_KEY

​
Parameters

​
promptId
string
required

The unique identifier of the prompt.

​
deploymentId
string
required

The unique identifier of the deployment.

​
Response

​
id
string

The unique identifier of the deployment.

​
createdAt
number

Unix timestamp when the deployment was created.

​
updatedAt
number

Unix timestamp when the deployment was last updated.

​
createdByUserId
string

ID of the user who created the deployment.

​
updatedByUserId
string

ID of the user who last updated the deployment.

​
projectId
string

The unique identifier of the project.

​
promptId
string

The unique identifier of the prompt.

​
deploymentEnvironmentId
string

The unique identifier of the deployment environment.

​
prompt
PromptType

The prompt, see PromptType for more details.

curl -X GET \
  "https://api.adaline.ai/v2/deployments?promptId=prompt_123&deploymentId=deploy_456" \
  -H "Authorization: Bearer your_workspace_api_key" \
  -H "Content-Type: application/json"


{
  "id": "deploy_456",
  "createdAt": 1704067200000,
  "updatedAt": 1704067200000,
  "createdByUserId": "user_789",
  "updatedByUserId": "user_789",
  "projectId": "project_abc",
  "promptId": "prompt_123",
  "deploymentEnvironmentId": "env_123",
  "prompt": {
    "config": {
      "model": "gpt-4o-mini",
      "providerName": "openai",
      "providerId": "6e94350a-95a9-48e7-8eab-a9f35ec2dc9d",
      "settings": {
        "temperature": 0.7,
        "maxTokens": 1000,
        "topP": 1,
        "frequencyPenalty": 0,
        "presencePenalty": 0
      }
    },
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "{{user_input}}"
      }
    ],
    "tools": [],
    "variables": [
      {
        "name": "user_input",
        "description": "The user's input",
        "content": {
          "modality": "text",
          "value": "Who wrote the book 'The Great Gatsby'?"
        }
      }
    ]
  }
}

​
Best Practices

  1. Cache Deployments: Cache deployment responses when possible to reduce API calls and improve performance.

  2. Error Handling: Always implement proper error handling for all possible HTTP status codes.

  3. Environment Management: Use different deployment environments (production, staging, development) to manage your prompt lifecycle.

  4. Rate Limit Awareness: Monitor your usage to avoid hitting rate limits, especially on free plans.