Nemotron 3 Nano Omni 30B A3B Reasoning
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.
Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.
- Organization
- Nvidia
- Family
- nemotron
- Providers
- 8
- Context
- 256,000
- Output limit
- 65,536
- Knowledge
- —
- Release
- 2026-04-28
- Updated
- 2026-04-28
- Weights
- Open
- Input
- text, image, video, audio
- Output
- text
- Capabilities
- Tools, Reasoning, Temperature
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Crusoe | nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B | 256,000 | 65,536 | $0.30 / $1.83 | Yes | Yes | — | View |
| Deep Infra | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 262,144 | 65,536 | $0.20 / $0.80 | Yes | Yes | Yes | View |
| DigitalOcean | nemotron-3-nano-omni | 65,536 | 65,536 | $0.50 / $0.90 | Yes | Yes | Yes | View |
| Kilo Gateway | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 256,000 | 65,536 | $0.00 / $0.00 | Yes | Yes | No | View |
| Nvidia | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | 256,000 | 65,536 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Nvidiavia OpenRouter | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free unknown | 256,000 | 65,536 | $0.00 / $0.00 | Yes | Yes | No | View |
| Requesty | nemotron-3-nano-omni-30b-a3b-reasoning | 131,072 | 20,480 | $0.00 / $0.00 | Yes | Yes | No | View |
| Vultr | nemotron-3-nano-omni-30b-a3b-reasoning | 262,144 | 65,536 | $0.10 / $0.25 | Yes | Yes | — | 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.
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.
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeObserved - Input
- $0.00
- Output
- $0.00
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Nvidianvidia | $0.00 | $0.00 | — | — |
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.
Time to first token · milliseconds
All latency percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Nvidianvidia | 417 ms | 927.75 ms | 2,284.9 ms | 14,225.9 ms |
Output throughput · tokens per second
All throughput percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Nvidianvidia | 41 t/s | 46 t/s | 63 t/s | 131 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.
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.
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeObserved Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| Composite indices | Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428 | Artificial Analysis | Intelligence — · Coding 13.8 · Agentic — | 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.
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeObserved - Context
- 256,000
- Maximum output
- 65,536
- Tokenizer
- Other
- Input
- text, audio, image, video
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-04-28
https://openrouter.ai/api/v1nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freenvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16Reasoning
- Required
- No
- Enabled by default
- Yes
- Default effort
- —
- Supported efforts
- —
Supported parameters
include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p
Default parameters
- top p
- 0.95
- temperature
- 0.6
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Nemotron 3 Nano Omni 30B A3B Reasoning 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 Omni 30B A3B Reasoning?
There are 8 cataloged offers across 8 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 256,000 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.
- ·
0a81995e1d02 - ·
2b26c6ad7f23