# Nemotron 3 Nano 30B a3b API

NVIDIA's Nemotron 3 Nano 30B a3b, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send nemotron-3-nano-30b-a3b as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: nemotron-3-nano-30b-a3b
- Maker: NVIDIA
- Context window: 128K tokens
- Input price: $0.050 per million tokens
- Output price: $0.200 per million tokens
- Providers: 1 independent provider
- Regions: global

## Providers

- [RelayGPU](https://liquidinference.ai/providers/42a59421-ba42-47c5-9e79-b05429ad3b59.md): global, $0.050 input and $0.200 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context

## Scores

- HLE: 4.8, #208 of 273
- GPQA: 46.9, #219 of 250
- AA-LCR: 39.7, #185 of 237
- Terminal-Bench Hard: 8.3, #121 of 166
- τ²-Bench: 45.3, #111 of 169
- IFBench: 63.2, #59 of 178
- SimpleQA Verified: 6.0, #126 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-nano-30b-a3b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Nemotron 3 Nano 30B a3b?

Nemotron 3 Nano 30B a3b is a model from NVIDIA.

### How much does Nemotron 3 Nano 30B a3b cost?

Offers now ask $0.050 per million input tokens and $0.200 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of Nemotron 3 Nano 30B a3b?

The largest offer takes 128,000 input tokens. One job can generate up to 16,384 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Nemotron 3 Nano 30B a3b do?

Its providers list Text.

### What inputs and outputs does Nemotron 3 Nano 30B a3b support?

Text → Text.

### Which providers serve Nemotron 3 Nano 30B a3b?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call Nemotron 3 Nano 30B a3b?

Send "nemotron-3-nano-30b-a3b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Nemotron 3 Nano 30B a3b listed?

The exchange first listed it on 9/29/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/nemotron-3-nano-30b-a3b)
- [Nemotron 3.5 Lightning](https://liquidinference.ai/models/nemotron-3.5-lightning.md)
- [Nemotron 3 Ultra 550B a55b](https://liquidinference.ai/models/nemotron-3-ultra-550b-a55b.md)
- [Llama 3.3 Nemotron Super 49B V1](https://liquidinference.ai/models/llama-3.3-nemotron-super-49b-v1.md)
- [Nemotron 3.5 Content Safety](https://liquidinference.ai/models/nemotron-3.5-content-safety.md)
- [Nemotron: Nano 9B V2](https://liquidinference.ai/models/nemotron-nano-9b-v2.md)
- [Nemotron 3.5 Lightning:thinking](https://liquidinference.ai/models/nemotron-3.5-lightning%3Athinking.md)
- [Set up a client](https://liquidinference.ai/connect/nemotron-3-nano-30b-a3b)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)