One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.035 = $0.035
- Output0.1M x $0.14 = $0.014
$0.049per session
Amazon - Closed weights
Amazon Nova Micro is a closed-weights model from Amazon that costs $0.035 per 1M input tokens and $0.14 per 1M output tokens on the first-party API, with a 128K-token context window.
Last verified from aws.amazon.com. All sources
| Item | Price / 1M tokens |
|---|---|
| Input | $0.035 |
| Output | $0.14 |
| Cache read | $0.00875 |
| Batch inputBatch requests | $0.0175 |
| Batch outputBatch requests | $0.07 |
Note: Text-only model. 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 $0.00875 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 '128K tokens' context and '10K' max output, recorded as 128,000 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.
amazon.nova-micro-v1:0amazon/nova-microWorked from the standard list rates above, with the math shown so you can swap in your own token counts.
1M input tokens and 100K output tokens, no caching.
$0.049per session
10,000 requests a day at 2K input and 500 output tokens each.
$1.40per day
$42.00 per 30-day month
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
$0.0254per session
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Amazon Nova Micro (this page) | $0.035 | $0.14 |
| Command R7BCohere | $0.0375 | $0.15 |
| Ministral 3 8BMistral AI | $0.15 | $0.15 |
| Qwen3.7-FlashAlibaba Cloud (Qwen) | $0.03 | $0.13 |
| Hy-MT2-LiteTencent | $0.044 | $0.177 |
| Amazon Nova LiteAmazon | $0.06 | $0.24 |
| Amazon Nova 2 LiteAmazon | $0.30 | $2.50 |
| Amazon Nova ProAmazon | $0.80 | $3.20 |
| Amazon Nova PremierAmazon | $2.50 | $12.50 |
Amazon Nova Micro costs $0.035 per 1M input tokens and $0.14 per 1M output tokens on Amazon's first-party API, per aws.amazon.com on October 17, 2026. Per 1M tokens, cache reads cost $0.00875, and the batch rate is $0.0175 input and $0.07 output.
Amazon Nova Micro has a 128,000-token context window and returns up to 10,000 output tokens per response.
No. Amazon Nova Micro is a closed-weights model. You call it through Amazon's API as amazon.nova-micro-v1:0 or through Vercel AI Gateway as amazon/nova-micro.
Amazon released Amazon Nova Micro on December 3, 2024.
Last verified from aws.amazon.com.
Newsletter
One email per week. New model releases, price cuts and what they mean for your bill.