Skip to main content
The Pioneer inference endpoint accepts a model ID, input text, and a schema that defines exactly what to extract. You can target a fine-tuned model from a completed training job or call a base model directly. For encoder models (GLiNER), use the schema field to declare entities, classifications, structures, or relations. For decoder models, use "task": "generate" instead.

​
Endpoints

MethodPathDescription
POST/inferenceRun inference on a model
GET/base-modelsList the model catalog

​
List the model catalog

Use GET /base-models to fetch the current list of available models. Filter by ?supports_inference=true to narrow to inference-ready models, and by ?task_type=encoder or ?task_type=decoder to filter by architecture. 
curl "https://api.pioneer.ai/base-models?supports_inference=true" \
  -H "X-API-Key: YOUR_API_KEY"

​
Run inference

​
Request parameters

​
model_id
string
required
The ID of the model to run inference against. Use the job ID returned by POST /felix/training-jobs (e.g. job_abc123) to target a fine-tuned model, or a base model ID like fastino/gliner2-base-v1 to call a base model directly.
​
text
string
required
The input text to run the model against.
​
schema
object
Defines what to extract from the input text. Used with encoder models. Accepts up to four optional keys — include any combination based on your task.
​
entities
string[]
List of entity type labels to extract (Named Entity Recognition). Example: ["organization", "product", "location"].
​
classifications
object[]
List of classification tasks. Each object has a task string (the classification label group name) and a labels array of candidate class strings.
​
structures
object
Dictionary of structure definitions for JSON extraction. Each key is a structure name; the value defines the shape of the output.
​
relations
object[]
List of relation definitions. Each object describes a directional relationship between entity types to extract.
​
threshold
number
default:"0.5"
Confidence threshold for returned predictions. Values range from 0 to 1. Lower values return more candidates at the cost of precision; higher values return fewer, higher-confidence results.

​
Example — NER with a fine-tuned model

curl -X POST https://api.pioneer.ai/inference \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "job_abc123",
    "text": "Apple announced the MacBook Pro at WWDC in Cupertino.",
    "schema": {
      "entities": ["organization", "product", "event", "location"]
    },
    "threshold": 0.5
  }'

​
Example — combined schema (entities + classifications)

curl -X POST https://api.pioneer.ai/inference \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "job_abc123",
    "text": "Apple announced the MacBook Pro at WWDC in Cupertino.",
    "schema": {
      "entities": ["organization", "product", "location"],
      "classifications": [
        {
          "task": "sentiment",
          "labels": ["positive", "negative", "neutral"]
        }
      ]
    },
    "threshold": 0.5
  }'
For decoder models, omit schema and pass "task": "generate" in the request body instead. The model will respond with generated text rather than a structured extraction result.
The threshold default is 0.5. Lower it (e.g. 0.3) to surface more candidates at the cost of more false positives. Raise it (e.g. 0.7) for tighter, higher-precision extractions.

​
Using a base model ID

If you haven’t fine-tuned a model yet, you can call a base model directly. Use a model ID from GET /base-models, such as fastino/gliner2-base-v1. 
curl -X POST https://api.pioneer.ai/inference \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "fastino/gliner2-base-v1",
    "text": "Tim Cook spoke at the Apple event in San Francisco.",
    "schema": {
      "entities": ["person", "organization", "location"]
    }
  }'