This Blueprint has been deprecated

Please transition to another model to avoid any service interruptions.
For more models information, visit our API Reference

nvidia

Build Continuous Refining AI Agents with Data Flywheels

LaunchableEnterprise

Build a production-integrated data flywheel that continuously optimizes AI agents for latency, accuracy, and cost — built with NVIDIA NeMo and open NVIDIA Nemotron models.

llama-3_1-70b-instruct•llama-3_3-70b-instruct•llama-3.2-1b-instruct•llama-3.2-3b-instruct•llama-3_1-8b-instruct•llama-3_2-nv-embedqa-1b-v2

Data Flywheel
NIM
NeMo microservices
enterprise
nemotron
nvidia ai

View GitHub Deploy on Cloud