Nova Micro
Amazon · Active · available in 20 of 31 regions
Tool usePrompt cachingBatch inferenceStreaming VisionEmbeddingsFine-tuning
- Context window
- 128K
- 128,000 tokens
- Max output
- —
- Input / 1M
- $0.035
- us-east-1
- Output / 1M
- $0.140
What Nova Micro is good for
editorialNova Micro offers a 128K-token context window with tool use and prompt caching, and is the cheapest option from this provider at $0.035 per 1M input tokens. Callable in 20 of 31 regions.
Suits
- Repeated prompts. Supports prompt caching, so a re-sent prefix costs about 4× less than fresh input. On agentic loops that resend a long system prompt every step, this moves the bill more than the headline price does.
- Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
- Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.
- Cost. The cheapest Amazon model here at $0.035 per 1M input tokens — the default choice for high-volume, low-difficulty work.
Think twice if
- Documents with layout. Text only. Scanned PDFs, screenshots and charts need a vision model or an OCR step first.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Summarisation and extraction
High-volume, structured output from unstructured input. Usually the cheapest workload to run well.
- · Turning a million support tickets into a fixed schema of product, severity and root cause.
- · Pulling line items, totals and dates off scanned invoices into JSON.
- · Condensing every meeting transcript into decisions taken and owners assigned.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Cross-region inference profiles (3)
Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $0.035 | $0.140 | $0.0087 | $0 | $0.017 | $0.070 | API |
| us-east-2 US East (Ohio) | $0.035 | $0.140 | $0.0087 | $0 | $0.017 | $0.070 | API |
| us-west-2 US West (Oregon) | $0.035 | $0.140 | $0.0087 | $0 | $0.017 | $0.070 | API |
| eu-west-1 EU (Ireland) | $0.040 | $0.160 | $0.010 | — | $0.020 | $0.080 | API |
| eu-west-2 EU (London) | $0.049 | $0.196 | — | — | — | — | API |
| eu-west-3 EU (Paris) | $0.052 | $0.208 | $0.013 | — | $0.026 | $0.104 | API |
| eu-central-1 EU (Frankfurt) | $0.046 | $0.184 | $0.011 | — | $0.023 | $0.092 | API |
| eu-north-1 EU (Stockholm) | $0.038 | $0.152 | $0.0095 | — | $0.019 | $0.076 | API |
| eu-south-1 EU (Milan) | $0.056 | $0.224 | $0.014 | — | — | — | API |
| eu-south-2 Europe (Spain) | $0.039 | $0.156 | $0.0097 | — | — | — | API |
| ap-east-2 Asia Pacific (Taipei) | — | — | — | $0 | — | — | API |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.042 | $0.168 | $0.010 | — | $0.021 | $0.084 | API |
| ap-northeast-2 Asia Pacific (Seoul) | $0.041 | $0.164 | $0.010 | — | $0.021 | $0.082 | API |
| ap-south-1 Asia Pacific (Mumbai) | $0.041 | $0.164 | $0.010 | — | $0.021 | $0.082 | API |
| ap-southeast-1 Asia Pacific (Singapore) | $0.047 | $0.188 | $0.012 | — | $0.024 | $0.094 | API |
| ap-southeast-2 Asia Pacific (Sydney) | $0.037 | $0.148 | $0.0092 | — | $0.018 | $0.074 | API |
| ap-southeast-5 Asia Pacific (Malaysia) | $0.042 | — | — | — | — | — | API |
| ap-southeast-7 Asia Pacific (Thailand) | — | — | — | — | $0.021 | $0.084 | API |
| il-central-1 Israel (Tel Aviv) | $0.044 | $0.176 | $0.011 | $0 | $0.022 | $0.088 | API |
Region availability
On-demand us-east-1 On-demand Inference profile only us-east-2 Profile only Not available us-west-1 Not available Inference profile only us-west-2 Profile only Not available ca-central-1 Not available Not available ca-west-1 Not available Not available mx-central-1 Not available Inference profile only eu-west-1 Profile only On-demand eu-west-2 On-demand Inference profile only eu-west-3 Profile only Inference profile only eu-central-1 Profile only Not available eu-central-2 Not available Inference profile only eu-north-1 Profile only Inference profile only eu-south-1 Profile only Inference profile only eu-south-2 Profile only Inference profile only ap-east-2 Profile only Inference profile only ap-northeast-1 Profile only Inference profile only ap-northeast-2 Profile only Not available ap-northeast-3 Not available Inference profile only ap-south-1 Profile only Not available ap-south-2 Not available Inference profile only ap-southeast-1 Profile only On-demand ap-southeast-2 On-demand Inference profile only ap-southeast-3 Profile only Not available ap-southeast-4 Not available Inference profile only ap-southeast-5 Profile only Not available ap-southeast-6 Not available Inference profile only ap-southeast-7 Profile only Inference profile only il-central-1 Profile only Not available af-south-1 Not available Not available sa-east-1 Not available
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, Nova Micro can be served without the request leaving 4 of the 25 jurisdictions with a Bedrock region.
Nova Micro appears in
Common questions
- How much does Nova Micro cost on Amazon Bedrock?
- $0.035 per 1M input tokens and $0.140 per 1M output tokens in us-east-1. Cached input reads at $0.0087, roughly a tenth of the input rate, which dominates the bill on agentic workloads that re-send a long prefix.
- Which AWS regions support Nova Micro?
- 20 of 31 regions: us-east-1, us-east-2, us-west-2, eu-west-1, eu-west-2, eu-west-3, eu-central-1, eu-north-1, eu-south-1, eu-south-2, ap-east-2, ap-northeast-1, ap-northeast-2, ap-south-1, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-5, ap-southeast-7, il-central-1. Regions marked profile-only need a cross-region inference profile ID such as apac.amazon.nova-micro-v1:0 rather than the bare model ID.
- What is the context window of Nova Micro?
- 128,000 tokens (128K).
- What is the model ID for Nova Micro on Bedrock?
- amazon.nova-micro-v1:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: apac.amazon.nova-micro-v1:0, eu.amazon.nova-micro-v1:0, us.amazon.nova-micro-v1:0.