AWS Bedrock (Nova) Cost Calculator
Estimate Amazon Nova Premier, Pro, Lite and Micro costs.
With the default inputs, $0.00240 per request — ~$72.00/month at 1,000 requests/day. Enter your own numbers below to recompute instantly; the full step-by-step math is shown under the worked example.
Results update automatically as you type.
- Input cost
- $0.000800
- Output cost
- $0.00160
- Per request
- $0.00240
- Per day
- $2.40
- Per month
- $72.00
Estimate the cost of Amazon's Nova models on AWS Bedrock. Nova Micro and Lite are extremely cheap for high-volume text, while Pro and Premier add vision, video and stronger reasoning.
How this is calculated
Cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price) for your chosen Nova model on Bedrock. Batch pricing swaps in the discounted async rate; monthly cost scales by requests per day × 30. This covers on-demand token pricing, not provisioned throughput commitments.
Is this a good result? What to do next
Nova Micro and Lite are extremely cheap for high-volume text — Micro is about $0.035/$0.14 per 1M tokens — while Pro and Premier add vision, video and stronger reasoning at higher rates. Using Premier for plain text is the usual overspend.
Typical planning ranges
- Nova Micro
- ~$0.035 / $0.14 per 1M tokens
- Nova Lite
- very cheap multimodal
- Nova Pro / Premier
- premium, multimodal + reasoning
Ranges are typical planning figures to sanity-check your result, not authoritative benchmarks. Your numbers will vary with use case, volume, and vendor.
How to improve this number
- Use Micro/Lite for high-volume text.
- Reserve Pro/Premier for multimodal or hard reasoning.
- Enable batch pricing for offline jobs.
Common mistakes
- Using Premier for plain-text tasks Micro could handle.
- Ignoring provisioned-throughput options for steady high volume.
When to use a different approach
To rank Nova against GPT, Claude and Gemini, use the model cost comparison. For a serverless AI feature, use the Lambda + LLM cost calculator.
Worked example (defaults)
With the default inputs above, here is the result:
- Input cost
- $0.000800
- Output cost
- $0.00160
- Per request
- $0.00240
- Per day
- $2.40
- Per month
- $72.00
- input: 1,000 / 1e6 x $0.8/M = $0.000800
- output: 500 / 1e6 x $3.2/M = $0.00160
- monthly = $0.00240 x 1,000 x 30 days
Sources & references
Frequently asked questions
Which Nova model is cheapest?+
Nova Micro is the cheapest at $0.035/$0.14 per 1M tokens, followed by Nova Lite. Pro and Premier cost more but add multimodal and reasoning.
Related calculators
Answering a real question?
This calculator powers these problem-solving guides: