Integrations · Nebius Builders

NVIDIA NIM

Self-hosted GPU inference microservices, turnkey.

AI Cloud

Inference

Anyscale

Scale AI workloads with Anyscale deployed on Managed Kubernetes.

AI Cloud

Orchestration

dstack

Install dstack and orchestrate AI workloads end-to-end.

AI Cloud

Orchestration

Run:ai

Optimize GPU resources for ML/AI workloads on Managed Kubernetes.

AI Cloud

Orchestration

SkyPilot

Run, manage and scale AI workloads with SkyPilot.

AI Cloud

Orchestration

Outerbounds (Metaflow)

Production-grade ML pipelines via the Outerbounds partnership.

AI Cloud

Orchestration

MPIrun

Configure a Compute GPU cluster and run NCCL tests with MPIrun.

AI Cloud

Training

MLflow

Managed experiment tracking and model registry.

AI Cloud

MLOps

Terraform

Official Nebius provider for IaC resource management.

AI Cloud

IaC

Pulumi

Manage Nebius resources from Pulumi via the Terraform bridge.

AI Cloud

IaC

Hugging Face

Open-source models and datasets via inference API.

Token Factory

Inference

AISuite

Multi-provider LLM router with a unified Python API.

Token Factory

Inference

LiteLLM

Unified LLM gateway with a Nebius AI provider — use model=nebius/<model-name> to route 30+ Token Factory models across any agent framework.

Token Factory

Gateway

OpenRouter

OpenRouter exposes Nebius models through its unified API.

Token Factory

Gateway

Portkey

LLM gateway with caching, retries, and budget guardrails.

Token Factory

Gateway

LangChain

Chat models, embeddings, retrievers via langchain-nebius.

Token Factory

Agents

LlamaIndex

RAG framework integration for Nebius inference.

Token Factory

Agents

CrewAI

Open-source agentic framework on Token Factory models.

Token Factory

Agents

Agno

Lightweight multi-modal agent framework.

Token Factory

Agents

Google ADK

Google's Agent Development Kit, wired to Nebius models.

Token Factory

Agents

Pydantic AI

Type-safe agent framework with Pydantic validation.

Token Factory

Agents

AWS Strands

Amazon's agent SDK, model-agnostic and Nebius-ready.

Token Factory

Agents

Camel AI

Multi-agent framework with role-playing and task pipelines.

Token Factory

Agents

Mastra

TypeScript agent framework with Nebius as a first-class provider.

Token Factory

Agents

Cursor (Token Factory)

Wire Token Factory in as a custom model provider in Cursor.

Token Factory

Coding

VS Code (Copilot Chat)

Hugging Face VS Code Chat extension routes Copilot through Nebius.

Token Factory

Coding

Zed (Token Factory)

Configure Zed's inline assistant against Token Factory models.

Token Factory

Coding

Cline

Open-source autonomous coding agent for VS Code + JetBrains with Nebius Token Factory as a native provider — pick Nebius, paste your key, drive Qwen3-Coder or GLM-4.5.

Token Factory

Coding

Continue

Open-source AI coding assistant for VS Code & JetBrains with a native Nebius provider — configure chat (DeepSeek R1) and embeddings (BAAI) in config.yaml.

Token Factory

Coding

Kilo Code

Multi-mode coding agent for VS Code on Token Factory models.

Token Factory

Coding

Linkup

Web search and content extraction API for agents.

Token Factory

Search

Postman

Pre-built Postman collection for the Token Factory API.

Token Factory

Tooling

Helicone

LLM observability: traces, costs, prompts, and evals.

Token Factory

Observability

Keywords AI

Production LLM monitoring — logs, evals, prompt tracking, alerts.

Token Factory

Observability

Tavily Web Search API

Real-time web search, extraction, and crawling for LLMs and agents.

Tavily

Search

Tavily MCP Server

Hosted MCP endpoint so any MCP-aware client can search the live web.

Tavily

Search

Tavily Agent Skills

Drop-in skills that give your agent web search, extraction, and crawling.

Tavily

Agents

OpenAI Agent Builder

Wire Tavily's MCP server into OpenAI Agent Builder.

Tavily

No-code

Agno

Use Tavily as a tool inside Agno agents.

Tavily

Agents

Anthropic

Add live web search to Anthropic Claude via Tavily's API.

Tavily

Agents

Arcade.dev

Governed web search, extraction, and research via Arcade's MCP Gateway.

Tavily

Gateway

Cartesia

Real-time voice agents that search the web via Cartesia's Line SDK.

Tavily

Agents

Claude

Use Tavily across the Claude ecosystem as a Connector or Plugin.

Tavily

Agents

Composio

Tavily available as a tool through Composio.

Tavily

No-code

CrewAI

Equip CrewAI agents with web search and extraction.

Tavily

Agents

Dify

No-code Tavily integration inside Dify workflows.

Tavily

No-code

FlowiseAI

Tavily as a tool inside Flowise visual agent builds.

Tavily

No-code

Google ADK

Connect Google's Agent Development Kit to Tavily's search API.

Tavily

Agents

Haystack

Use Tavily inside Haystack pipelines via `tavily-haystack`.

Tavily

Agents

LangChain

LangChain's recommended search tool — official partnership.

Tavily

Agents

Langflow

Visual multi-agent + RAG builds with Tavily search nodes.

Tavily

No-code

LibreChat

Search, extract, and use Tavily as a built-in agent tool.

Tavily

Agents

LlamaIndex

Search the web from LlamaIndex RAG/agent flows.

Tavily

Agents

Make

No-code Tavily steps in Make scenarios.

Tavily

No-code

Mastra

First-class Mastra tools for search, extract, crawl, and map.

Tavily

Agents

n8n

No-code Tavily nodes for n8n automation workflows.

Tavily

No-code

OpenAI

Add real-time web search to OpenAI Responses + Agents.

Tavily

Agents

OpenClaw

Web search across WhatsApp, Telegram, Discord, iMessage agents.

Tavily

Agents

Pydantic AI

Type-safe Tavily tool calls inside Pydantic AI agents.

Tavily

Agents

StackAI

Plug Tavily into StackAI workflows for real-time web data.

Tavily

No-code

Tines

Automated, no-code intelligence workflows in Tines.

Tavily

No-code

Vellum

Built-in web search inside the Vellum Assistant desktop app.

Tavily

Agents

Vercel AI SDK

Search, extraction, crawl, and map for Vercel AI agents.

Tavily

Agents

Zapier

No-code Tavily steps across thousands of Zapier integrations.

Tavily

No-code

OpenCode

Terminal coding agent with a built-in Token Factory provider — drive open models like Kimi K2 and Qwen3-Coder from the CLI.

Token Factory

Coding

Hugging Face smolagents

Minimalist code-agent framework; set provider="nebius" to run CodeAgents on Token Factory open models.

Token Factory

Agents

LLM Gateway

Open-source unified LLM gateway; its Nebius provider exposes Token Factory models behind one OpenAI-compatible API.

Token Factory

Gateway

Pipecat

Real-time voice + multimodal agent framework with a NebiusLLMService for low-latency Token Factory inference.

Token Factory

Agents

Devin

Cognition's autonomous coding agent uses Tavily for research-before-coding via the MCP marketplace connector.

Tavily

Coding

ElevenLabs

ElevenLabs voice agents add live web retrieval by wiring in a Tavily Search API key as a tool.

Tavily

Agents

Gradium

Voice-AI platform for live speech agents; uses Tavily as its real-time web-context layer.

Tavily

Agents

Requesty

LLM routing gateway; its Nebius provider exposes Token Factory open models behind a unified API.

Token Factory

Gateway

Dask Cloud Provider

Spin up Dask clusters on Nebius AI Cloud VMs for distributed Python + data workloads.

AI Cloud

Orchestration

Retool

Build internal tools with a Tavily action for live web search inside Retool apps + workflows.

Tavily

Tooling

Pipedream

Connect Tavily search + extract into thousands of Pipedream automation workflows.

Tavily

Tooling

BuildShip

Low-code visual backend builder with a Tavily node for web search + extraction.

Tavily

No-code

Sim

Visual agent builder; drop in the Tavily tool to give agents live web retrieval.

Tavily

No-code

Activepieces

Open-source automation platform with a Tavily MCP piece for web search in flows.

Tavily

No-code

Qdrant

Deploy the Qdrant vector database on Nebius AI Cloud for RAG + similarity search.

AI Cloud

Tooling

Open WebUI

Self-host the Open WebUI chat front-end on Nebius AI Cloud over your own models.

AI Cloud

Tooling

Flowise (Nebius AI Cloud)

Deploy the Flowise low-code agent builder on Nebius AI Cloud GPU infrastructure.

AI Cloud

No-code

ComfyUI

Run the ComfyUI node-based diffusion workflow tool on Nebius AI Cloud GPUs.

AI Cloud

Tooling

JupyterLab (Nebius AI Cloud)

Launch a GPU-backed JupyterLab environment on Nebius AI Cloud for notebooks + experiments.

AI Cloud

Tooling

dlt (dltHub)

Open-source Python ELT library with a Nebius source/destination for data pipelines.

AI Cloud

Tooling

Zed IDE

GPU-accelerated, collaborative code editor with a Token Factory integration guide for connecting open models to its built-in AI assistant.

Token Factory

Coding