Runnable reference · the Token Factory Cookbook

Every recipe, rendered and browsable.

The full Token Factory Cookbook — 60 recipes across 17 categories, 30 notebooks rendered with their outputs. The runnable backing for the reference architectures on the ecosystem page. Built on open models through one OpenAI-compatible base_url.

Essentials · 5

Core Token Factory notebooks — adding a LoRA, batch inference, guided JSON, image LoRA.

API Quickstarts · 1

Point one base_url at Token Factory — the OpenAI-compatible on-ramp, plus aisuite, LiteLLM, and LlamaIndex SDKs.

Agents · 26

Production agents across every major framework — LangChain, CrewAI, Agno, AWS Strands, Google ADK, LlamaIndex, Pydantic, and more.

agents

Agent Cost Comparison 2

Benchmark Nebius-hosted LLMs on a small data-analysis task and compare their cost, latency, token usage, and correctness.

source ↗
agents3 nb

Agno Agents

This folder has the following agents:

source ↗
agents

AI Data Analyst Chatbot for E-Commerce Analytics

A production-grade AI Data Analyst Chatbot workflow for n8n, leveraging Nebius Token Factory's DeepSeek-V3-0324-fast LLM for advanced, structured data analysis and Google Workspace automation.

source ↗
agents

AWS Strands Starter Agent

A simple demonstration of using the Strands library with Nebius Token Factory's API to create an AI assistant that can fetch weather information.

source ↗
agents

CAMEL-AI Model Comparison Agent

A benchmarking tool built with the CAMEL framework that compares the performance of various AI models, including OpenAI and Nebius models. This tool measures and visualizes the speed of different models in terms of tokens processed per seco

source ↗
agentsagent-cost-comparison-1

Comparing Agent Cost Across Models

This script runs the same agentic task against multiple Nebius-hosted models and compares token usage, tool calls, wall-clock time, and estimated cost.

source ↗
agentslangchain

Competitive Intelligence Agent

A LangChain Deep Agent that produces decision-grade competitive briefs, powered by an LLM served by Nebius Token Factory, and real-time web research via Tavily.

source ↗
agents1 nb

CrewAI Starter Agent

A simple yet powerful AI research crew built with CrewAI that leverages multiple specialized agents to discover and analyze groundbreaking technologies.

source ↗
agentslangchain

Customer Support Resolution Agent

Production use case: support teams need agents that combine ticket text, order state, policies, and safe workflow recommendations.

source ↗
agentslangchain

Customer Support Resolution Agent

A SaaS-style customer support agent that answers product questions, looks up real order status, and escalates to a human ticket when it can't confidently resolve the issue.

source ↗
agentslangchain

Data Quality Operations Agent

Production use case: data teams need read-only agents that can inspect pipelines, query governed datasets, and recommend next actions when metrics break.

source ↗
agents1 nb

HackerNews Analysis Agent

A powerful AI agent built with Agno that analyzes and provides insights about HackerNews content. This agent uses the Nebius AI model to deliver intelligent analysis of tech news, trends, and discussions.

source ↗
agentslangchain

Incident Response Commander Agent

Production use case: SRE teams need fast, evidence-backed triage during incidents without giving an LLM the ability to mutate infrastructure directly.

source ↗
agentslangchain

Insurance Claims Assistant

A multimodal claims-triage agent built on Nebius Token Factory. Drop in a folder of claim documents — in any shape — and the agent reads everything (PDFs, photos, forms), works out what the claim is, confirms its understanding with you, the

source ↗
agentslangchain

LangChain Data Agent PoC

This is a small natural-language-to-SQL data agent inspired by the architecture of eosho/langchaindataagent, but implemented from scratch for this cookbook.

source ↗
agentslangchain

LangChain deepagents + Nebius Token Factory

Two starter examples of a LangChain Deep Agent powered by an LLM served by Nebius Token Factory.

source ↗
agents

LangChain deepagents + Nemotron @ Nebius Token Factory

A starter example of a LangChain Deep Agent powered by an Nvidia Nemotron LLM served by Nebius Token Factory.

source ↗
agentslangchain

LangChain examples for Nebius Token Factory

This folder contains production-oriented LangChain examples powered by Nebius Token Factory. Each example is self-contained with its own requirements.txt, .env.example, source files, and sample data.

source ↗
agents

LlamaIndex Starter Agent

A powerful AI agent template built with LlamaIndex that demonstrates how to create intelligent agents using the LlamaIndex framework. This starter project implements a Task Management Assistant using the Nebius AI model to showcase LlamaInd

source ↗
agentslangchain

PitchLoop Voice Coach

PitchLoop is a conversational voice-agent example powered by Gradium, Nebius Token Factory, and LangChain.

source ↗
agents1 nb

PydanticAI Starter Agent

A powerful AI agent built with PydanticAI that provides real-time weather information for any city. This agent uses the Nebius AI model to deliver accurate weather forecasts and insights.

source ↗
agents

Simple Tool Calling Agent with Google ADK (Agent Development Kit) + Nebius AI

This example shows a sample 'tool calling' agent, built using Google's Agent Development Kit (ADK) framework.

source ↗
agents

Universal Deep Research (Nebius Token Factory) — Agent

This agent demonstrates a multi‑step research pipeline powered by Nebius Token Factory models (OpenAI‑compatible) with a FastAPI backend and a Next.js frontend. It uses the model moonshotai/Kimi-K2.6 by default.

source ↗
agentslangchain

Vendor Risk Compliance Agent

Production use case: security, privacy, and procurement teams need fast vendor reviews grounded in internal controls and contract evidence.

source ↗
agentslangchain

VoyageCompass Travel Planner

A Streamlit travel planning app built with LangChain and Nebius. It is inspired by AI travel-agent demos, but it uses a different app structure and planning flow:

source ↗
agentslangchain

🗂️ Briefing Room — Pre-Meeting Intel Agent

You have a call with a company in 30 minutes. What do you need to know?

source ↗
Tool Calling · 1

Function calling and live web tools (Tavily) on open models.

RAG · 5

Retrieval-augmented generation over PDFs and vector stores — Milvus, Qdrant, Weaviate, LlamaIndex.

LoRA Fine-tuning · 1

Train and serve LoRA adapters on open models.

Fine-tuning & Post-training · 1

Full fine-tuning pipelines on Token Factory.

Distillation · 1

Generate training data, distill, and evaluate smaller models.

Models · 2

Model-specific quickstarts — GLM-4.5, GPT-OSS, Qwen3, Nemotron.

Integrations · 7

Token Factory inside OpenClaw, Tavily, and more.

integrations

Build an enterprise knowledge base with OpenWiki and Kimi K2.7 Code

OpenWiki is a LangChain documentation agent that generates and maintains a Markdown knowledge base from source repositories or connected knowledge sources. This guide configures OpenWiki to use moonshotai/Kimi-K2.7-Code through the Nebius T

source ↗
integrations

Invoice Extraction with Confidence-Gated Human Validation

A vision model reading a blurred invoice does not stay silent. It produces a number.

source ↗
integrations

OpenClaw + Nebius Token Factory

OpenClaw is a self-hosted AI assistant that connects chat apps (WhatsApp, Telegram, Discord, and more) to LLM providers. Because Nebius Token Factory serves open models through an OpenAI-compatible API, you can point OpenClaw at Token Facto

source ↗
integrations

OpenHands Agent Canvas + Nebius Token Factory

OpenHands Agent Canvas is a self-hosted control center for coding agents — a web UI for starting agent conversations, running coding tasks, and setting up automations. Because Nebius Token Factory is a first-class LLM provider in Agent Canv

source ↗
integrations

Pixeltable + Nebius Token Factory

Pixeltable is open-source multimodal AI data infrastructure. You declare tables with images, video, audio, documents, and text; computed columns and embedding indexes run incrementally as data arrives. Pixeltable includes a native Nebius To

source ↗
integrationsopenenv1 nb

Prompt Optimization with OpenEnv and Open Models

Tune an IT access-request agent against environment rewards on Nebius Token Factory, no fine-tuning required.

source ↗
integrations

Tavily + Token Factory

Tavily is an LLM-optimized search API built specifically for agents. It delivers clean, structured, and context-aware web results — making it ideal for research, competitive intelligence, and multi-step agentic workflows. Tavily handles que

source ↗
Apps · 1

End-to-end applications built on Token Factory.

Coding · 1

Coding-agent and code-generation recipes.

Workshops · 2

Hands-on workshop material.

Articles · 1

Written deep-dives.

Community · 2

Community-contributed guides.

Fun · 2

Pelicans on bicycles, snake games — open models having fun.

Office Hours · 1