One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.06 = $0.06
- Output0.1M x $0.24 = $0.024
$0.084per session
Amazon - Closed weights
Amazon Nova Lite pricing and specs
Amazon Nova Lite is a closed-weights model from Amazon that costs $0.06 per 1M input tokens and $0.24 per 1M output tokens on the first-party API, with a 300K-token context window.
Last verified from aws.amazon.com. All sources
- Input / 1M
- $0.06
- Output / 1M
- $0.24
- Context
- 300K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.06 |
| Output | $0.24 |
| Cache read | $0.015 |
| Batch inputBatch requests | $0.03 |
| Batch outputBatch requests | $0.12 |
Note: Prices are US East (N. Virginia), Standard tier, Geo cross-Region inference and in-Region. No Global profile. No Priority or Flex price is listed for this model. The $0.015 cache-read price is printed in the page's model-customization On Demand Inference table, which states custom models are priced the same as base models. No cache-write price is listed for Nova. The model card states '300K tokens' context and '10K' max output, recorded as 300,000 and 10,000. The release date is from the AWS What's New launch post (Dec 3, 2024). The Bedrock model card gives the launch date as Dec 05, 2024.
Specs
- Context window
- 300,000 tokens
- Max output
- 10,000 tokens
- Release date
- Provider
- Amazon
- API model id
amazon.nova-lite-v1:0- Vercel AI Gateway id
amazon/nova-lite- Weights
- Closed weights
What Amazon Nova Lite costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.06 = $1.20
- Output5M x $0.24 = $1.20
$2.40per day
$72.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.015 = $0.0135
- Uncached input0.1M x $0.06 = $0.006
- Output0.1M x $0.24 = $0.024
$0.0435per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Amazon Nova Lite (this page) | $0.06 | $0.24 |
| Ministral 3 14BMistral AI | $0.20 | $0.20 |
| MiMo-V2.6-FlashXiaomi MiMo | $0.14 | $0.28 |
| Hy-MT2-PlusTencent | $0.074 | $0.295 |
| Hy-MT2-ProTencent | $0.074 | $0.295 |
| Amazon Nova MicroAmazon | $0.035 | $0.14 |
| Amazon Nova 2 LiteAmazon | $0.30 | $2.50 |
| Amazon Nova ProAmazon | $0.80 | $3.20 |
| Amazon Nova PremierAmazon | $2.50 | $12.50 |
Related reading
- OpenAI's Daybreak Cyber Models Land on Amazon Bedrock: GPT-5.6-Cyber Gets Its First Cloud PathOpenAI Daybreak cyber models are on Amazon Bedrock: GPT-5.6-Cyber and GPT-5.6 Sol for eligible customers, gated by Trusted Access for Cyber enrollment.
- AWS Kiro Developer Guide: The Spec-Driven IDE That Replaced Amazon QAWS Kiro is the spec-driven agentic IDE replacing Amazon Q Developer. How it differs, how pricing compares, and the migration timeline before April 2027.
FAQ
How much does Amazon Nova Lite cost per million tokens?
Amazon Nova Lite costs $0.06 per 1M input tokens and $0.24 per 1M output tokens on Amazon's first-party API, per aws.amazon.com on October 17, 2026. Per 1M tokens, cache reads cost $0.015, and the batch rate is $0.03 input and $0.12 output.
What is Amazon Nova Lite's context window?
Amazon Nova Lite has a 300,000-token context window and returns up to 10,000 output tokens per response.
Are Amazon Nova Lite's weights open?
No. Amazon Nova Lite is a closed-weights model. You call it through Amazon's API as amazon.nova-lite-v1:0 or through Vercel AI Gateway as amazon/nova-lite.
When was Amazon Nova Lite released?
Amazon released Amazon Nova Lite on December 3, 2024.
Sources
Last verified from aws.amazon.com.
- https://aws.amazon.com/bedrock/pricing/
- https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html
- https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html
- https://aws.amazon.com/about-aws/whats-new/2024/12/amazon-nova-foundation-models-bedrock/
- https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.