Currently listed through:
Model details
Nova Micro (US)
Amazon Nova Micro is positioned as the smallest member of Amazon's Nova text generation family, designed for lightweight, high-throughput language tasks where minimal latency and cost matter more than maximum reasoning depth. Within the Nova lineup it sits below the Nova Lite tier, signaling an emphasis on efficient short-form generation, classification, routing, extraction, and similar utility workloads rather than long, analytical answers. The model is distributed under the identifier us.amazon.nova-micro-v1:0, a regional US endpoint key that indicates it is served from Amazon's US infrastructure for general availability.
Its practical strengths are anchored in a large the cataloged API limit context window, which lets it ingest substantial documents, code files, or multi-turn histories in a single call while still returning compact, focused responses. The micro tier is best suited for teams that need an affordable text-only workhorse for tasks such as summarization, intent detection, structured extraction, retrieval-augmented preprocessing, and tool-augmented pipelines where the surrounding orchestration handles heavier reasoning. For builders comparing cost versus quality across the Nova family, Nova Micro represents the entry point optimized for scale and routine automation rather than complex open-ended generation.
Quick Info
Powered by- Provider
- Amazon Bedrock
- Model key
- us.amazon.nova-micro-v1:0
- Release date
- Dec 3, 2024
- Last updated
- Dec 3, 2024
- Knowledge cutoff
- 2024-10
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.035
- Output token cost
- $0.14
Limits
- Output tokens
- 10,000 tokens
- Context window
- 128,000 tokens
Transparent token rates
Compare Nova Micro (US) pricing
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Latest news about Nova Micro (US)
No articles yet. Fetch the latest news to show it here.