List Models
Retrieve a paginated list of available models and adapters, with filtering by object type, trainability, inference engine, service type, name, and architecture.
Endpoint
GET https://api.platform.knowledgator.com/models/
Public Endpoint: This catalog endpoint is publicly accessible and does not require authentication. Do not pass
KnowledgatorAPI-KeyorAuthorization: Bearerheaders (sending auth headers causes401 Unauthorized: auth.invalid_token).
Public Catalog vs. Your Custom Models
GET /models/queries the public open models catalog (base models likecomprehend-itorextract-it, and official adapters). Use these model IDs as the base model when starting fine-tuning.- Your Custom Trained Models: When you fine-tune a model, your custom models and runs are managed under
/trainings/. To view your trained models and runs, use List Trainings (GET /trainings/).
Headers
| Name | Type | Required | Description |
|---|---|---|---|
Content-Type | String | No | application/json |
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
offset | Integer | No | Pagination offset (default: 0, min: 0) |
limit | Integer | No | Maximum results per page (default: 100, max: 10000) |
object_type | String | No | Filter by object type: adapter (LoRA adapter) or model (open model) |
trainable | String | No | Filter trainable models: adapter or model |
inference | String | No | Filter by supported inference engine (e.g. comprehend-it, extract-it) |
name | String | No | Filter by model name (1-64 chars) |
type | String | No | Filter by service type: ner, text-classification, relation-extraction |
architecture | String | No | Filter by underlying architecture (e.g. gliner, gliclass) |
tag | String | No | Filter by tag keyword |
task | String | No | Filter by specific task |
modality | String | No | Filter by modality (e.g. text) |
include_base | Boolean | No | Include base models not trained by customer (default: true) |
Response
{
"models": [
{
"id": "comprehend-it",
"name": "comprehend-it",
"type": "text-classification",
"description": "Zero-shot text classification and reasoning model",
"num_of_parameters": "494M",
"training_model": true,
"training_adapter": true,
"inference": "comprehend-it",
"created_at": "2024-01-15T10:30:00Z",
"updated_at": "2024-01-15T10:30:00Z",
"is_base": true
}
],
"total": 1,
"offset": 0,
"limit": 100
}
Response Fields
models: Array of model objectsid: Unique model identifiername: Model nametype: Service type (ner,text-classification, etc.)num_of_parameters: Number of parameters (e.g."494M","1.1B", or numeric)training_model: Boolean indicating if full model training is supportedtraining_adapter: Boolean indicating if LoRA adapter training is supportedinference: Inference service compatibilityfine_tuned: Boolean indicating if this is a fine-tuned model/adapterparent_model: Parent base model ID if fine-tuneddescription: Full markdown model descriptionshort_description: Brief summary descriptioncreated_at: ISO 8601 timestamp of creationupdated_at: ISO 8601 timestamp of last updateis_base: Whether this is a base model (not trained by customer)
total: Total number of models matching the filteroffset: Current pagination offsetlimit: Current pagination limit
Error Codes
| Status Code | Description |
|---|---|
| 200 | OK – Request successful. |
| 400 | Bad Request – Invalid input or validation failed. |
| 401 | Unauthorized – Invalid API key or email verification required. |
| 500 | Internal Server Error – Server-side issue. |
| 503 | Service Unavailable – Service temporarily unavailable. |
Example Usage
SDK Usage
💡 Dedicated SDK Guides: See Python SDK | TypeScript SDK
TypeScript/JavaScript
import { createClient } from '@knowledgator/typescript-sdk';
const kg = createClient('YOUR_API_KEY');
// List all models
const result = await kg.finetuning.listModels();
console.log(result.models);
// List with filtering
const filtered = await kg.finetuning.listModels({
type: 'ner',
include_base: true,
limit: 50
});
console.log(filtered.models);
Python
from knowledgator import Knowledgator
kg = Knowledgator(api_key="YOUR_API_KEY")
# List all models
result = kg.finetuning.list_models()
print(result.models)
# List with filtering
filtered = kg.finetuning.list_models(
type="ner",
include_base=True,
limit=50
)
print(filtered.models)
Expected SDK Output
[
{
"id": "comprehend-it",
"name": "comprehend-it",
"type": "text-classification",
"description": "Zero-shot text classification and reasoning model",
"created_at": "2024-01-15T10:30:00Z",
"updated_at": "2024-01-15T10:30:00Z",
"is_base": true
}
]
Python
import requests
url = "https://api.platform.knowledgator.com/models/"
# List all models
response = requests.get(url)
print(response.json())
# List with filtering (e.g. LoRA adapters trainable with comprehend-it)
params = {
"object_type": "adapter",
"trainable": "adapter",
"inference": "comprehend-it",
"limit": 50
}
response = requests.get(url, params=params)
print(response.json())
cURL
# List all models (Public - no API key needed)
curl -X GET "https://api.platform.knowledgator.com/models/"
# List with filtering
curl -X GET "https://api.platform.knowledgator.com/models/?object_type=adapter&trainable=adapter&inference=comprehend-it&limit=50"
Expected Response (cURL)
{
"models": [
{
"id": "comprehend-it",
"name": "comprehend-it",
"type": "text-classification",
"description": "Zero-shot text classification and reasoning model",
"created_at": "2024-01-15T10:30:00Z",
"updated_at": "2024-01-15T10:30:00Z",
"is_base": true
}
],
"total": 1,
"offset": 0,
"limit": 50
}
Additional Information
- Pagination: Use
offsetandlimitparameters to paginate through large result sets - Filtering: Combine multiple filter parameters to narrow down results (e.g. by
object_type,trainable,inference) - Base Models: Browse the public base models and adapters available as starting points for fine-tuning
- Custom Trained Models: To manage models you have fine-tuned yourself, see List Trainings
- Use Cases:
- Browse available base models for fine-tuning
- Find models by type, name, architecture, or task
- Discover compatible inference models