Get Started
API Reference
Project Archetypes
- Introduction
- Archetypes
Endpoints
- v2
- Tasks
- Deliveries
- Annotations
- v1
Get a Task
Retrieve a Task from its task_id
.
API_KEY='live_...'
TASK_ID='abc123'
curl --request GET \
--url "https://api.scale.com/v2/task?task_id=$TASK_ID" \
--header "Authorization: Bearer $API_KEY"
{
"task_id": "task_123",
"project": "project_123",
"batch": "batch_123",
"status": "completed",
"created_at": "2025-01-01T08:31:03.169Z",
"completed_at": "2025-01-02T04:00:39.923Z",
"threads": [
{
"id": "thread_0",
"turns": [
{
"id": "turn_0",
"messages": [
{
"content": {
"text": "This is an example prompt"
},
"role": "user",
"source_id": "user",
"annotations": []
},
{
"content": {
"text": "This is the base model response"
},
"role": "assistant",
"source_id": "base_model",
"model_parameters": {
"model": "scale-gpt-1.5-turbo",
"temperature": 0.9,
"max_completion_tokens": 2048
},
"annotations": [
{
"key": "instruction_following",
"value": 3
},
{
"key": "truthfulness",
"value": 2
},
{
"key": "conciseness",
"value": 3
},
{
"key": "format",
"value": 3
},
{
"key": "safety",
"value": 3
},
{
"key": "overall",
"value": 5
}
]
},
{
"content": {
"text": "This is test model response"
},
"role": "assistant",
"source_id": "test_model",
"model_parameters": {
"model": "scale-gpt-2.0",
"temperature": 0.9,
"max_completion_tokens": 2048
},
"annotations": [
{
"key": "instruction_following",
"value": 2
},
{
"key": "truthfulness",
"value": 1
},
{
"key": "truthfulness_justification",
"value": "The response incorrectly classifies..."
},
{
"key": "conciseness",
"value": 2
},
{
"key": "format",
"value": 3
},
{
"key": "safety",
"value": 3
},
{
"key": "overall",
"value": 3
}
]
}
],
"annotations": [
{
"key": "selected_model_id",
"value": "base_model"
},
{
"key": "likert_value",
"value": 2
},
{
"key": "justification",
"value": "@Response 1 is better than @Response 2. @Response 2 has an issue in Truthfulness ..."
}
]
}
],
"annotations": []
}
]
}
Every request sent to Scale’s API requires authentication. In short, your API Key is the Bearer token. See the Authentication section for more details.
Authorizations
Your API Key is the Bearer token. See the Authentication section to learn how to access your key.
Query Parameters
Scale's unique identifier for the task.
List of fields to expand in the response.
Entities that can be expanded from an ID to an object.
project
, batch
List of properties to include in the task response.
Property that can be included in the annotations
attachment_details
, model_parameters
Response
Represents a single task
Unique identifier for the task.
Current status of the task.
pending
, completed
, canceled
, error
UTC timestamp when the task was created.
UTC timestamp when the task was completed.
Task metadata defined during task creation.
Threads associated with the task. Tasks that do not have a status
of completed
will have an empty threads
array.
Represents a thread of messages in a task.
Unique identifier for the thread.
Turns within the thread.
A unique identifier for the turn.
A list of messages associated with this turn.
The role of the sender in the conversation (e.g., user, assistant).
system
, user
, assistant
, function
The content of the message, including text and any attachments.
The ID of the source system or user that sent the message.
Annotations specific to this message.
Represents a generic annotation.
Unique identifier for the annotation.
Key for the annotation.
The type of the value and the possible_values, if they exist.
Title of the annotation.
Further details about the question.
String representation of the possible options.
A string representation of the annotation.
Integer type annotation value.
The possible values for this annotation.
Integer type annotation value.
The name of the model that generated the message.
The temperature of the model that generated the message.
The maximum number of tokens the model can generate.
Annotations applied to the entire turn.
Represents a generic annotation.
Unique identifier for the annotation.
Key for the annotation.
The type of the value and the possible_values, if they exist.
Title of the annotation.
Further details about the question.
String representation of the possible options.
A string representation of the annotation.
Unique identifier for an annotation.
Integer type annotation value.
The possible values for this annotation.
Integer type annotation value.
Annotations for the entire thread.
Represents a generic annotation.
Unique identifier for the annotation.
Key for the annotation.
The type of the value and the possible_values, if they exist.
Title of the annotation.
Further details about the question.
String representation of the possible options.
A string representation of the annotation.
Unique identifier for an annotation.
Integer type annotation value.
The possible values for this annotation.
Integer type annotation value.
Errors associated with the task. Available when the task status is error
Details of the error on the task. Available when the task status is error
API_KEY='live_...'
TASK_ID='abc123'
curl --request GET \
--url "https://api.scale.com/v2/task?task_id=$TASK_ID" \
--header "Authorization: Bearer $API_KEY"
{
"task_id": "task_123",
"project": "project_123",
"batch": "batch_123",
"status": "completed",
"created_at": "2025-01-01T08:31:03.169Z",
"completed_at": "2025-01-02T04:00:39.923Z",
"threads": [
{
"id": "thread_0",
"turns": [
{
"id": "turn_0",
"messages": [
{
"content": {
"text": "This is an example prompt"
},
"role": "user",
"source_id": "user",
"annotations": []
},
{
"content": {
"text": "This is the base model response"
},
"role": "assistant",
"source_id": "base_model",
"model_parameters": {
"model": "scale-gpt-1.5-turbo",
"temperature": 0.9,
"max_completion_tokens": 2048
},
"annotations": [
{
"key": "instruction_following",
"value": 3
},
{
"key": "truthfulness",
"value": 2
},
{
"key": "conciseness",
"value": 3
},
{
"key": "format",
"value": 3
},
{
"key": "safety",
"value": 3
},
{
"key": "overall",
"value": 5
}
]
},
{
"content": {
"text": "This is test model response"
},
"role": "assistant",
"source_id": "test_model",
"model_parameters": {
"model": "scale-gpt-2.0",
"temperature": 0.9,
"max_completion_tokens": 2048
},
"annotations": [
{
"key": "instruction_following",
"value": 2
},
{
"key": "truthfulness",
"value": 1
},
{
"key": "truthfulness_justification",
"value": "The response incorrectly classifies..."
},
{
"key": "conciseness",
"value": 2
},
{
"key": "format",
"value": 3
},
{
"key": "safety",
"value": 3
},
{
"key": "overall",
"value": 3
}
]
}
],
"annotations": [
{
"key": "selected_model_id",
"value": "base_model"
},
{
"key": "likert_value",
"value": 2
},
{
"key": "justification",
"value": "@Response 1 is better than @Response 2. @Response 2 has an issue in Truthfulness ..."
}
]
}
],
"annotations": []
}
]
}