Nemotron 3 Nano 30B A3B

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.

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

Organization: Nvidia
Family: nemotron
Providers: 16
Context: 262,144
Output limit: 262,144
Knowledge: —
Release: 2025-12-15
Updated: 2025-12-15
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

19 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Amazon Bedrock	nvidia.nemotron-nano-3-30b	262,144	8,192	$0.06 / $0.24	Yes	Yes	Yes	View
Crusoe	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B	262,144	262,144	$0.05 / $0.20	Yes	Yes	—	View
Deep Infra	nvidia/Nemotron-3-Nano-30B-A3B	262,144	262,144	$0.05 / $0.20	Yes	Yes	—	View
DigitalOcean	nemotron-3-nano-30b	262,144	262,144	— / —	Yes	Yes	—	View
Eden AI	deepinfra/nvidia/Nemotron-3-Nano-30B-A3B	262,144	262,144	$0.05 / $0.20	Yes	Yes	Yes	View
Infomaniak	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8	1,000,000	262,144	$0.06 / $0.25	Yes	Yes	—	View
Kenari	nemotron-3-nano-30b-a3b	262,144	262,144	$0.00 / $0.00	Yes	Yes	—	View
Kilo Gateway	nvidia/nemotron-3-nano-30b-a3b	262,144	235,929	$0.05 / $0.20	Yes	Yes	Yes	View
Merge Gateway	nvidia/nemotron-3-nano-30b-a3b	256,000	32,000	$0.05 / $0.20	Yes	No	No	View
NanoGPT	nvidia/nemotron-3-nano-30b-a3b	262,144	235,929	$0.17 / $0.68	No	No	No	View
Nvidia	nvidia/nemotron-3-nano-30b-a3b	131,072	131,072	$0.00 / $0.00	Yes	Yes	—	View
Ollama Cloud	nemotron-3-nano:30b	1,048,576	131,072	$0.06 / $0.24	Yes	Yes	—	View
Crusoevia OpenRouter	nvidia/nemotron-3-nano-30b-a3b fp8	262,144	235,929	$0.05 / $0.20	Yes	Yes	Yes	View
DeepInfravia OpenRouter	nvidia/nemotron-3-nano-30b-a3b fp4	262,144	228,000	$0.05 / $0.20	Yes	Yes	No	View
Nebiusvia OpenRouter	nvidia/nemotron-3-nano-30b-a3b fp8	262,144	235,929	$0.06 / $0.24	Yes	Yes	Yes	View
Novitavia OpenRouter	nvidia/nemotron-3-nano-30b-a3b fp4	262,144	32,768	$0.05 / $0.20	Yes	Yes	No	View
Pioneer	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	262,144	131,072	$0.05 / $0.20	Yes	Yes	—	View
Venice AI	nvidia-nemotron-3-nano-30b-a3b	128,000	16,384	$0.075 / $0.30	No	Yes	Yes	View
Vercel AI Gateway	nvidia/nemotron-3-nano-30b-a3b	262,144	262,144	$0.05 / $0.20	Yes	No	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers19Across 16 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 4 lowest-priced configurations

InputOutput

Crusoecrusoe/fp8

$0.05$0.20

DeepInfradeepinfra/fp4

$0.05$0.20

Novitanovita/fp4

$0.05$0.20

Nebiusnebius/fp8

$0.06$0.24

nvidia/nemotron-3-nano-30b-a3bObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.05
Output: $0.20
Cache read: $0.03

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Crusoecrusoe/fp8	$0.05	$0.20	$0.03	—
DeepInfradeepinfra/fp4	$0.05	$0.20	$0.025	—
Nebiusnebius/fp8	$0.06	$0.24	—	—
Novitanovita/fp4	$0.05	$0.20	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

Crusoecrusoe/fp8

217–5,507.75 ms

DeepInfradeepinfra/fp4

4,698.5–130,195.06 ms

Nebiusnebius/fp8

632.5–1,359.22 ms

Novitanovita/fp4

383–5,296.98 ms

All latency percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
Crusoecrusoe/fp8	217 ms	304 ms	3,450.6 ms	5,507.75 ms
DeepInfradeepinfra/fp4	4,698.5 ms	21,039.5 ms	45,111.3 ms	130,195.06 ms
Nebiusnebius/fp8	632.5 ms	795 ms	1,130.1 ms	1,359.22 ms
Novitanovita/fp4	383 ms	614.5 ms	859.4 ms	5,296.98 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

Crusoecrusoe/fp8

214–330.56 t/s

DeepInfradeepinfra/fp4

21–39 t/s

Nebiusnebius/fp8

97–149 t/s

Novitanovita/fp4

252.5–349.85 t/s

All throughput percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
Crusoecrusoe/fp8	214 t/s	255 t/s	297 t/s	330.56 t/s
DeepInfradeepinfra/fp4	21 t/s	26 t/s	30.4 t/s	39 t/s
Nebiusnebius/fp8	97 t/s	115.25 t/s	126 t/s	149 t/s
Novitanovita/fp4	252.5 t/s	295 t/s	318 t/s	349.85 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 4 endpoints

Endpoint5 minutes30 minutes24 hours

Crusoecrusoe/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.98%

DeepInfradeepinfra/fp4Observed Oct 4, 2026, 11:31 AM UTC

—

99.52%

85.44%

Nebiusnebius/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.45%

Novitanovita/fp4Observed Oct 4, 2026, 11:31 AM UTC

100%

99.95%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

nvidia/nemotron-3-nano-30b-a3bObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 20

Coding

14.4

Agentic

Intelligence

8.9

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondNVIDIA: Nemotron 3 Nano 30B A3B

62.858%

tau bench verified airlineNVIDIA: Nemotron 3 Nano 30B A3B

51.75%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	OpenRouter	62.858%	Details
Composite indices	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)nvidia/nemotron-3-nano-30b-a3b	Artificial Analysis	Intelligence 8.9 · Coding 14.4 · Agentic 1	Details
tau bench verified airline	NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	OpenRouter	51.75%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

nvidia/nemotron-3-nano-30b-a3bObserved Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 235,929
Tokenizer: Other
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2025-12-14

Base URLhttps://openrouter.ai/api/v1

Model IDnvidia/nemotron-3-nano-30b-a3b

Version IDnvidia/nemotron-3-nano-30b-a3b

Weights IDnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Reasoning

Required: No
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Nemotron 3 Nano 30B A3B cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Nemotron 3 Nano 30B A3B?

There are 19 cataloged offers across 16 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · ac7ef5380c83
Sep 12, 2026 · f8d7f958134b