# Nova 2 Lite V1 API

Amazon's Nova 2 Lite V1, 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 nova-2-lite-v1 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: nova-2-lite-v1
- Maker: Amazon
- Context window: 1M tokens
- Input price: $0.380 per million tokens
- Output price: $3.160 per million tokens
- Providers: 1 independent provider
- Regions: global

## Providers

- [EmpirioLabs AI](https://liquidinference.ai/providers/4f49f07c-0d26-44bd-88a8-34f3f5fbd3b7.md): global, $0.380 input and $3.160 output per million tokens, $0.213 cache read per million tokens, 1M tokens of context

## Scores

- HLE: 2.9, #264 of 273
- GPQA: 60.3, #177 of 250
- AA-LCR: 18.7, #215 of 237
- Terminal-Bench Hard: 6.8, #131 of 166
- LiveCodeBench: 34.6, #79 of 130
- AIME 2025: 33.7, #65 of 100
- MMLU-Pro: 74.3, #75 of 133
- τ²-Bench: 62.0, #90 of 169
- IFBench: 40.5, #118 of 178
- SimpleQA Verified: 31.5, #74 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": "nova-2-lite-v1",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Nova 2 Lite V1?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does Nova 2 Lite V1 cost?

Offers now ask $0.380 per million input tokens and $3.160 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 Nova 2 Lite V1?

The largest offer takes 1,000,000 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Nova 2 Lite V1 do?

Its providers list Documents, Vision, Video input, Reasoning effort, JSON object, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does Nova 2 Lite V1 support?

Text · Files · Images · Video → Text.

### Which providers serve Nova 2 Lite V1?

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 Nova 2 Lite V1?

Send "nova-2-lite-v1" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Nova 2 Lite V1 listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/nova-2-lite-v1)
- [Nova: Micro 1 0](https://liquidinference.ai/models/nova-micro-1-0.md)
- [Nova: Lite V1](https://liquidinference.ai/models/nova-lite-v1.md)
- [Nova: Lite 1 0](https://liquidinference.ai/models/nova-lite-1-0.md)
- [Nova: Pro V1](https://liquidinference.ai/models/nova-pro-v1.md)
- [Nova: Pro 1 0](https://liquidinference.ai/models/nova-pro-1-0.md)
- [Set up a client](https://liquidinference.ai/connect/nova-2-lite-v1)
- [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)