nvidia
NVIDIA: Nemotron 3 Nano Omni (free)
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free is NVIDIA’s Nemotron 3 Nano Omni variant exposed through OpenRouter’s free catalog. NVIDIA describes it as a 31B-parameter Mamba2-Transformer hybrid MoE with about 3B active parameters per token, accepting text, images, audio, and short video while producing text. Reasoning is enabled by default but can be disabled. Vendor documentation positions it for enterprise perception and context tasks; the available evidence is primarily catalog and vendor documentation rather than broad independent evaluation.[1][2]
Strengths
- Four input modalities—text, image, audio, and video—with text output; the documentation lists OCR, speech transcription, graphical-interface understanding, JSON output, tool calling, and word-level transcription timestamps.[1][2]
- Reasoning is enabled by default without being mandatory; API-facing controls include reasoning, tools, temperature, seed, and maximum tokens.[1][2]
- Both sources report a 256k-token context; the hybrid MoE architecture activates only part of its total parameters for each token.[1][2]
Limitations
- NVIDIA’s documentation states that language support is English only.[2]
- The vendor limits each video input to two minutes and each audio file to one hour; output is text only, and self-hosting requires documented NVIDIA GPU and runtime support.[2]
- The evidence combines catalog data with NVIDIA documentation and little independent testing; OpenRouter reports a coding measurement without enough methodology for a broad quality assessment. Validate quality, latency, media handling, and safety on the intended workload.[1][2]
Where to use it
- A possible fit for enterprise assistants that summarize or answer questions across meeting recordings, training videos, images, and long documents.[2]
- Worth evaluating for document-intelligence workflows involving OCR, charts, contracts, or financial documents.[2]
- A candidate for agent systems that interpret graphical interfaces, transcribe speech, or call tools to produce text.[1][2]
Sources
- [1] OpenRouter catalog · NVIDIA: Nemotron 3 Nano Omni (free)Sources checked: Nov 13, 2026
- [2] Model documentation · NVIDIA: Nemotron 3 Nano Omni (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- Canonical ID
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428
- Creator
- nvidia
- Added to OpenRouter
- 28.04.2026
- Context length
- 256,000
- Modality
- text+image+audio+video->text
- Input modalities
- text, audio, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | CC — below the B band | — |
| Agents | No measurement | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 13.8 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nvidia | 256,000 | $0 | $0 | — | — | 56.67% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.