nemotron-3-nano-30b-a3bNVIDIA
- endpoints
- 3
- regions
- 1
- api
- chat
- released
- December 2025
capabilities 2/8
The same weights cost 1.3x more on deepinfra inc. than on deepinfra inc.. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  NVIDIA | Global | 262K | free | free | free | - |
| 2 |  DeepInfra Inc. | Global | 262K | $0.04 | $0.16 | $0.02 | zdr |
| 3 | DeepInfra Inc. | Global | 262K | $0.05 | $0.20 | - | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| Math Index | 91.0 | |
| AIME 2025 | 91.0 | |
| MMLU Pro | 79.4 | |
| GPQA Diamond | 75.7 | |
| LiveCodeBench | 74.1 | |
| τ²-Bench | 40.9 | |
| SciCode | 30.6 | |
| Coding Index | 14.4 | |
| Terminal-Bench Hard | 13.6 | |
| Humanity's Last Exam | 11.4 | |
| Intelligence Index | 8.9 | |
| 11 evals | mean | 48.3 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-12-15.
nvidia/nemotron-3-nano-30b-a3bthis model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="nvidia/nemotron-3-nano-30b-a3b", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces compu
questions 5
Which providers serve nemotron-3-nano-30b-a3b?
How much does nemotron-3-nano-30b-a3b cost?
Is nemotron-3-nano-30b-a3b open weights?
What is the context window of nemotron-3-nano-30b-a3b?
How do I use nemotron-3-nano-30b-a3b with the OpenAI SDK?
more from nvidia 6
| model | context | from /M | providers |
|---|---|---|---|
| nemotron-lightning-3.5-30b-a3b | 262K | $0.05 | 1 |
| nemotron-3.5-lightning-30b-a3b | 1.0M | free | 1 |
| nvidia-nemotron-3-ultra | 262K | $0.37 | 1 |
| nemotron-3.5-content-safety | 131K | free | 1 |
| nemotron-3-ultra-nvfp4 | 262K | $0.60 | 1 |
| nemotron-3-nano-omni-30b-a3b-reasoning | 131K | free | 1 |
route nemotron-3-nano-30b-a3b through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology