For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
EnterpriseQuick Start
API ReferenceTutorials
  • Introduction
    • Getting started
  • API Reference
      • POST✨ Create batch of failed predictions
      • POST✨ Create batch predictions
      • GET✨ Get Project Subset Task List with Predictions and Accuracy details
      • GET✨ Get available subsets of a project (for prompts usage)
      • GET✨ List prompts
      • POST✨ Create prompt
      • GET✨ List projects compatible with prompt
      • GET✨ Get prompt
      • DEL✨ Delete prompt
      • PATCH✨ Update prompt
        • GET✨ Get inference run info
        • POST✨ Run prompt inference
        • POST✨ Cancel Inference Run API
LogoLogo
EnterpriseQuick Start
API ReferencePromptsRuns

✨ Get inference run info

GET
http://localhost:8000/api/prompts/:prompt_id/versions/:version_id/inference-runs
GET
/api/prompts/:prompt_id/versions/:version_id/inference-runs
$curl http://localhost:8000/api/prompts/1/versions/1/inference-runs \
>     -H "Authorization: Token  <api_key>" \
>     -H "Content-Type: application/json"
200Retrieved
1[
2  {
3    "completed_at": "2024-04-20T14:45:00Z",
4    "created_at": "2024-04-20T13:00:00Z",
5    "created_by": {
6      "avatar": "https://labelstud.io/media/avatars/janedoe.png",
7      "id": 42,
8      "username": "janedoe",
9      "email": "janedoe@example.com",
10      "first_name": "Jane",
11      "last_name": "Doe"
12    },
13    "id": 101,
14    "parent_model": 15,
15    "project": 3,
16    "source_model_run": 99,
17    "status": "Completed",
18    "task_ids": null,
19    "triggered_at": "2024-04-20T13:05:00Z",
20    "filters_json": null,
21    "job_id": "adala-job-7890",
22    "organization": 7,
23    "predictions_updated_at": "2024-04-20T14:40:00Z",
24    "project_subset": "All",
25    "sample_subset_size": 500,
26    "total_correct_predictions": 480,
27    "total_predictions": 500,
28    "total_tasks": 500
29  }
30]
<Card href="https://humansignal.com/goenterprise"> <img style="pointer-events: none; margin-left: 0px; margin-right: 0px;" src="https://docs.humansignal.com/images/badge.svg" alt="Label Studio Enterprise badge"/> <p style="margin-top: 10px; font-size: 14px;"> This endpoint is not available in Label Studio Community Edition. [Learn more about Label Studio Enterprise](https://humansignal.com/goenterprise) </p> </Card> Get information (status, metadata, etc) about an existing inference run
Was this page helpful?
Previous

✨ Run prompt inference

Next
Built with
Label Studio Enterprise badge

This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise

Get information (status, metadata, etc) about an existing inference run

Authentication

AuthorizationToken
The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>

Path parameters

prompt_idintegerRequired
version_idintegerRequired

Query parameters

orderingstringOptional
Which field to use when ordering the results.
parent_modelintegerOptional
The ID of the parent model for this Inference Run
projectintegerOptional
The ID of the project this Inference Run makes predictions on
project_subsetenumOptional

Defines which tasks are operated on (e.g. HasGT will only operate on tasks with a ground truth annotation, but All will operate on all records)

Allowed values:

Response

completed_atdatetime or nullRead-only
created_atdatetimeRead-only
created_byobject
A ModelSerializer that takes additional arguments for "fields", "omit" and "expand" in order to control which fields are displayed, and whether to replace simple values with complex, nested serializations
idintegerRead-only
parent_modelintegerRead-only
projectinteger
source_model_runinteger or nullRead-only
statusenum
  • Pending - Pending
  • InProgress - InProgress
  • Completed - Completed
  • Failed - Failed
  • Canceled - Canceled
Allowed values:
task_idsany or nullRead-only

List of task IDs for Custom subset re-evaluation.

triggered_atdatetime or nullRead-only
filters_jsonany or null

DM filter group for Filtered subset. Stored for display/re-run purposes.

job_idstring or null<=255 characters
Job ID for inference job for a ModelRun e.g. Adala job ID
organizationinteger or null
predictions_updated_atdatetime or null
project_subsetenum
  • All - All
  • HasGT - HasGT
  • Sample - Sample
  • Custom - Custom
Allowed values:
sample_subset_sizeinteger or null0-2147483647

Custom sample size for Sample subset. Uses PROMPTER_SAMPLE_SUBSET_SIZE if not set.

total_correct_predictionsinteger or null-2147483648-2147483647
total_predictionsinteger or null-2147483648-2147483647
total_tasksinteger or null-2147483648-2147483647
The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: 
curl https://label-studio-host/api/projects -H “Authorization: Token [your-token]”