Skip to main content
Pioneer stores every inference call and lets you retrieve results by ID or in bulk. You can also submit correction feedback on individual inferences — this feedback signals what the model got wrong and powers Adaptive Inference, which automatically retrains your model on corrected examples from live traffic.

​
Endpoints

MethodPathDescription
GET/inferencesList past inferences
GET/inferences/:idGet inference details
POST/inferences/:id/feedbackSubmit correction feedback

​
List past inferences

GET /inferences returns a paginated list of past inference calls. Use the query parameters below to filter results.

​
Query parameters

​
limit
number
Maximum number of results to return per page.
​
offset
number
Number of results to skip before returning. Use with limit to paginate through results.
​
model_id
string
Filter by model ID. Accepts a training job ID or a base model ID.
​
task
string
Filter by task type (e.g. ner, classification, generate).
​
project_id
string
Filter by project ID to see only inferences scoped to a specific project.
​
training_job_id
string
Filter by training job ID to see only inferences run against a specific fine-tuned model.

​
Example

curl "https://api.pioneer.ai/inferences?limit=20&offset=0&model_id=job_abc123" \
  -H "X-API-Key: YOUR_API_KEY"

​
Get inference details

GET /inferences/:id returns the full record for a single past inference, including the input text, schema, model response, and timestamp. 
curl https://api.pioneer.ai/inferences/INFERENCE_ID \
  -H "X-API-Key: YOUR_API_KEY"

​
Submit correction feedback

POST /inferences/:id/feedback lets you submit a corrected version of what the model should have predicted. Corrections are used as labeled training examples for Adaptive Inference.
Feedback submitted here powers Adaptive Inference — Pioneer’s continuous improvement loop that automatically retrains your model on corrections collected from live traffic. See the Adaptive Inference guide for details on how this works.

​
Request parameters

​
correction
object
required
The corrected output. The shape should match the schema used in the original inference — for example, a corrected entities list for an NER inference.

​
Example

curl -X POST https://api.pioneer.ai/inferences/INFERENCE_ID/feedback \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "correction": {
      "entities": [
        {"text": "Apple", "label": "organization", "start": 0, "end": 5},
        {"text": "iPhone", "label": "product", "start": 18, "end": 24}
      ]
    }
  }'