Skip to content
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Models
  • Providers
  • Pricing
  • Enterprise

Company

  • About
  • Announcements
  • CareersHiring
  • Partners
  • Privacy
  • Terms of Service
  • Support
  • State of AI

Developer

  • Documentation
  • API Reference
  • SDK
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

NVIDIA: Nemotron 3 Nano 30B A3B (free)Free variant

nvidia/nemotron-3-nano-30b-a3b:free

Created Dec 14, 2025256,000 context
$0/M input tokens$0/M output tokens

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Note: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.

Recent activity on Nemotron 3 Nano 30B A3B (free)

Total usage per day on OpenRouter

Prompt
142M
Reasoning
33.2M
Completion
9.68M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.