AAmazon · Released Dec 5, 2024
Nova Lite 1.0
Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
- Released
- Dec 5 2024
- Context window
- 300K 5K out
- Input / 1M tokens
- $0.06
- Output / 1M tokens
- $0.24 from $0.24
Where to run it
5 providers compared
Cheapest: NanoGPT at $0.06 / $0.24 per 1M input / output tokens — 28% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| NanoGPTno tool calling | $0.06 | $0.24 | $0.03 | 300K | 5K | — | Cheapest |
| Amazon Bedrock | $0.06 | $0.24 | — | 300K | 5K | 100%24h | +0% |
| Amazon Bedrockeu-west-1 | $0.06 | $0.24 | — | 300K | 5K | 98.6%24h | +0% |
| Kilo Gateway | $0.06 | $0.24 | — | 300K | 5K | — | +0% |
| Cortecs | $0.069 | $0.28 | — | 300K | 10K | — | +15% |
| AI/ML API | $0.083 | $0.33 | — | 300K | 5K | — | +39% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nova Lite 1.0. Scores appear here automatically once it does.
Specs
Details
- Model ID
amazon/nova-lite-v1- Developer
- Amazon
- Release date
- Dec 5, 2024 ·
- Context window
- 300,000 tokens
- Max output
- 5,120 tokens
- API price
- $0.06 / $0.24 per 1M input / output tokens
- Providers
- 5
- Input types
- text, image
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.