Amazon Nova Micro is a budget-tier language model from FastInfra. Amazon Nova Micro is a proprietary model available exclusively through FastInfra's API. Amazon Nova is AWS's proprietary model family, tightly integrated with the Bedrock platform — optimized for enterprise AWS workloads with strong multimodal support and competitive pricing.
Amazon Nova Micro is priced at $0.04/1M input tokens and $0.15/1M output tokens. Output tokens are 3.8× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, Amazon Nova Micro costs approximately $0.12 per 1,000 API calls. FastInfra does not publish a prompt caching rate for this model, so repeated long contexts are billed at the standard $0.04/1M input rate.
Its 128K-token context window handles most long-document tasks — roughly 75,000 words or a full novel — without requiring chunking or retrieval augmentation.
Amazon Nova Micro is best suited to cost, speed. Supported capabilities include function calling / tool use for agentic workflows, streaming token output for real-time UIs. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how Amazon Nova Micro compares to similar models across these dimensions.
Amazon Nova Micro sits in the budget tier — the most cost-efficient models, best for high-volume simple tasks, classification, extraction, and applications where cost per call is the primary constraint. Unlike open-weights alternatives, Amazon Nova Micro is only available via FastInfra's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing Amazon Nova Micro to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (N/A/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.
Input price vs 119 budget models tracked. Avg: $0.110/1M.
| Model ID | Amazon Nova Micro |
| Provider | FastInfra |
| Model Family | Amazon Nova |
| Tier | Budget |
| Context Window | 128,000 tokens (128K) |
| Max Output Tokens | — |
| Input Price | $0.04 / 1M tokens |
| Output Price | $0.15 / 1M tokens |
| Cached Input Price | Not available |
| Throughput | — |
| Latency (P50) | — |
| Intelligence Score | — |
| LiveBench Score | — |
| Cost per Task (LiveBench) | — |
| Data Confidence | — |
| HLE Score | — |
| GPQA Diamond | — |
| SWE-bench Score | — |
| OSWorld Score | — |
| BrowseComp Score | — |
| Terminal-Bench Score | — |
| AutoBench Score | — |
| Parameters | — |
| Vision Support | No |
| Function Calling | Yes |
| Streaming | Yes |
| Reasoning Model | No |
| Open Weights | No |
| Data Source | Static (verified) |
| Last Updated | 2026-10-22 |
Self-hosting Amazon Nova Micro? These GPUs are well-matched for this model's compute and memory requirements.