Integrations
API Reference
- GETGet status
- POSTGet impact metrics for a task
- POSTCalculate AI model impact metrics for BigQuery
- Manage models
- Manage GPUs
- Manage nodes
Get impact metrics for a task
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Query Parameters
Return debug information
Body
The start time of the request in UTC
The time the request took (as measured by client or proxy)
The time taken in processing the request (as measured at execution)
The cost to execute this request
The currency for the cost data
The integration used to source the data
Environment (prod/production indicates production)
The ID of the session (multiple requests)
The trace ID of the request (multiple requests in one task)
The unique identifier of this request
The client to attribute this call to
The project to attribute this call to
The application to attribute this call to
The ID of the model requested
The family of the model
The name of the model
The Hugging Face path of the model
The ID of the model that did the inference
The URL of the model endpoint
Cloud region as defined by the Scope3 API
1 - 64The ID of a managed service provider
Cloud ID as defined by the Scope3 API
1 - 64The instance type in the cloud
The ID of a custom or global node
Two-letter country code as defined by ISO 3166-1 alpha-2
2Two-letter region code as defined by ISO 3166-1 alpha-2
2Common types of AI/ML models and their primary functions:
- Text-based models for natural language processing
- Vision models for image analysis and generation
- Audio models for speech and sound processing
- Multimodal models that combine different types of inputs/outputs
- Specialized models for specific use cases
text-generation, chat, text-embedding, text-classification, sentiment-analysis, named-entity-recognition, question-answering, summarization, translation, image-classification, object-detection, image-segmentation, image-generation, image-to-text, text-to-image, style-transfer, face-detection, facial-recognition, speech-to-text, text-to-speech, speaker-identification, audio-classification, music-generation, multimodal-embedding, multimodal-generation, visual-question-answering, recommendation-system, reinforcement-learning, anomaly-detection, time-series-forecasting, clustering the number of input (or prompt) tokens
0 < x < 100000000the duration of audio input in seconds
0 < x < 100000the number of output (or completion) tokens
0 < x < 100000000the number of steps to use in the model
1 < x < 10000a list of output image sizes
the duration of audio output in seconds
0 < x < 100000the number of audio tokens in the output
0 < x < 100000000the number of video frames (frame rate x duration)
0 < x < 100000000the resolution of the video in number of lines (for instance, 1080 for 1080p)
Response
List of aliases for this model; must be globally-unique with id
ID of the customer who owns this node (visible to admins only)
ID of the user who created the node (admin or owner only)
fp8, fp8-e4m3, fp8-e5m2, fp16, tf32, fp32, fp64, bfloat8, bfloat16, bf16, int4, int8, int16, int32, int64, uint4, uint8, uint16, uint32, uint64 Common types of AI/ML models and their primary functions:
- Text-based models for natural language processing
- Vision models for image analysis and generation
- Audio models for speech and sound processing
- Multimodal models that combine different types of inputs/outputs
- Specialized models for specific use cases
text-generation, chat, text-embedding, text-classification, sentiment-analysis, named-entity-recognition, question-answering, summarization, translation, image-classification, object-detection, image-segmentation, image-generation, image-to-text, text-to-image, style-transfer, face-detection, facial-recognition, speech-to-text, text-to-speech, speaker-identification, audio-classification, music-generation, multimodal-embedding, multimodal-generation, visual-question-answering, recommendation-system, reinforcement-learning, anomaly-detection, time-series-forecasting, clustering Create a new node. Note on permissions:
- cloud_instance_id and managed_service_id can only be set by admins or users who own those resources
- Custom nodes are visible only to their owners
- Global nodes are visible to all users
- Admins can see and manage all nodes
3 - 640 < x < 100001 < x < 10000Cloud ID as defined by the Scope3 API
1 - 640 < x < 100000 < x < 10 < x < 1000000 < x < 1000001 < x < 30ID of the customer who owns this node (visible to admins only)
ID of the user who created the node (admin or owner only)
Two-letter country code as defined by ISO 3166-1 alpha-2
20 < x < 2000Two-letter region code as defined by ISO 3166-1 alpha-2
2