Get available models for agents - return direct array to match frontend expectations

Get Available Models

Nugen API Docs

Powering Specialised Intelligence at Scale

Nugen Intelligence

List Models

Create Agent Endpoint

List Agents

Get Agent

Delete agent - return boolean as expected by frontend

Delete Agent Endpoint

Update Agent Endpoint

Get Usage Stats

Execute an AI agent with a user message.

This endpoint runs inference using a specific agent, applying its
custom instructions, demonstrations, and model configuration to
generate a personalized response.

Authentication: Requires a valid API key in Authorization header.
Usage tracking and billing will be applied to the API key owner.

Run Agent Endpoint

List all documents with their details and categories.

List Documents

Upload Document

Update Document Categories

Get the download URL for a specific document.

Download Document

Delete Document

List all API keys for the authenticated user.

List Api Keys

Create a new API key for the authenticated user.

Create Api Key

Update an API key for the authenticated user.

Update Api Key

Delete an API key for the authenticated user.

Delete Api Key

Create task ID for benchmark generation - work handled by Celery

Create Benchmark Task

Get Benchmark Status

Create task ID for synthetic data generation - work handled by Celery

Create Synthetic Data

Get status of synthetic data generation task

Get Synthetic Data Status

Create task ID for alignment project creation - work handled by Celery

Create Alignment Project Task

Get status of alignment project creation task

Get Alignment Project Status

Generate dense vector embeddings for input text using specified embedding models

Generate Text Embeddings

Generate conversational responses that can process both text and images using vision-language models

Generate Vision-Language Chat Completions

Generate text completions with real-time streaming support for immediate response chunks

Generate Streaming Text Completions

Generate conversational responses with real-time streaming support for immediate response chunks

Models

Agents

Documents

API Keys

Benchmark

Synthetic Data

Alignment Project

Inference

Get Available Models

Response