Nemotron 3 Nano 30B A3B pricing, context and benchmark
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.
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Nemotron 3 Nano 30B A3B |
| Model ID | nvidia/nemotron-3-nano-30b-a3b |
| Provider | NVIDIA |
| Release date | 14 December 2025 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 235,929 tokens |
| Official input pricing | $0.06 per 1M tokens |
| Official output pricing | $0.24 per 1M tokens |
| Cache read pricing | $0.012 per 1M tokens |
| Market input pricing | $0.06 per 1M (cheapest route) |
| Market output pricing | $0.24 per 1M (cheapest route) |
| Reasoning tokens | Billed as output at $0.24 per 1M |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Yes, effort levels exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.06 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
What is 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...
Nemotron 3 Nano 30B A3B carries a 262K token window, uses the Other tokenizer and is served by NVIDIA. On Hoodgen it sits in the Fast tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
Release and what changed from the previous version
This is the only release of Nemotron 3 Nano 30B A3B on OpenRouter, released 14 December 2025. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
Features and capabilities
Thinking and reasoning capabilities
Nemotron 3 Nano 30B A3B can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $0.24 per million, and the trace can be returned with include_reasoning.
| Level | First token | Cost per task | Best for |
|---|---|---|---|
| Measured | n/a | n/a | Artificial Analysis measures the default reasoning configuration |
| Low effort | Faster | Lower | Chat, autocomplete, classification |
| High effort | Slower | Higher | Debugging, planning, multi step agents |
What can you do with Nemotron 3 Nano 30B A3B?
Prompt caching and how to cut the bill
Cached input bills at $0.012 per million instead of $0.06. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
Nemotron 3 Nano 30B A3B pricing
Official pricing
- $0.012 cached input
- 262K context
- text input
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Nebius | standard | $0.06 | $0.24 | $0.012 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0010 | $0.49 | 468 |
| List price | $0.0010 | $0.49 | 468 |
API and developer information
| Model ID | nvidia/nemotron-3-nano-30b-a3b |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · include_reasoning · logit_bias · max_tokens · presence_penalty · reasoning · repetition_penalty · response_format · seed · stop · structured_outputs · temperature · tool_choice · tools · top_k · top_p |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 235,929 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-nano-30b-a3b",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 235,929 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
| Depth ceiling | Fast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning. |
Nemotron 3 Nano 30B A3B vs other NVIDIA models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Nemotron 3 Nano 30B A3B | 262K | $0.06 | $0.24 | n/a | 2025 |
| Nemotron 3.5 Super VL | 1.05M | $0.06 | $0.35 | 14 | Oct 2026 |
| Nemotron 3.5 Lightning | 262K | $0.025 | $0.12 | 6 | 2026 |
| Nemotron 3.5 Super VL (free) | 1M | Free | Free | n/a | Oct 2026 |
| Nemotron 3 Nano Omni (free) | 256K | Free | Free | n/a | 2026 |
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to NVIDIA and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
Nemotron 3 Nano 30B A3B questions, answered
Start chatting with Nemotron 3 Nano 30B A3B
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.