Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see Privacy PolicyOpens in new tab. By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the NVIDIA API Trial Terms of ServiceOpens in new tab

Favicon for nvidia

NVIDIA: Nemotron 3 Nano 30B A3B

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

Model weights
Compare

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.

Modalities

In / Out Price

$0.05 / $0.20per 1M

Context

262K

Released

Dec 14, 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for NVIDIA: Nemotron 3 Nano 30B A3B (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Intelligence Index8.9
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Coding Index14.4
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Agentic Index1.0
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) GPQA Diamond75.7%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) HLE11.4%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) IFBench71.1%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) τ²-Bench Telecom40.9%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) AA-LCR38.0%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) GDPval-AA0.0%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) CritPt0.9%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) SciCode30.6%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Terminal-Bench Hard13.6%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) AA-Omniscience Accuracy17.3%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) AA-Omniscience Non-Hallucination Rate16.7%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) GPQA Diamond39.9%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) HLE4.6%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) IFBench37.5%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) τ²-Bench Telecom25.4%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) AA-LCR10.7%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) GDPval-AA0.0%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) CritPt0.0%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) Terminal-Bench Hard12.1%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) AA-Omniscience Accuracy11.4%
Artificial AnalysisNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) AA-Omniscience Non-Hallucination Rate9.0%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking

Frequently asked questions

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.

Nemotron 3 Nano 30B A3B costs $0.05/M input tokens and $0.20/M output tokens, with separate rates for Cache Read at $0.03/M tokens.

Nemotron 3 Nano 30B A3B has a 262,144 token context window. It supports up to 262,144 completion tokens.

Yes. Nemotron 3 Nano 30B A3B accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.

Nemotron 3 Nano 30B A3B is served by 4 providers on OpenRouter: Crusoe, NovitaAI, DeepInfra and Nebius Token Factory. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Nemotron 3 Nano 30B A3B was released on December 14, 2025.