Amazon の Amazon Nova Lite は、テキストと画像のネイティブ・マルチモーダル理解および図表・ドキュメント解析向けに設計されたAIモデルです。300K のコンテキストウィンドウ、毎秒 135 トークンの生成速度、知能指数 38/100（1Mトークンあたり入力$0.06・出力$0.24）を実現しています。
Technical Specifications
- Provider
- Amazon
- Category
- lightweight
- Release Date
- 2024-12
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- API Pay-as-you-go
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- nova-lite
- Supported SDK & API Protocol
- Amazon REST API (OpenAI-Compatible)
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Amazon lineup)
- Production Rate Limits (RPM & TPM)
- 5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.06/1M in) across full 300K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.015/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- API Prompt Engineering & RAG Distillation
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) · Video (~258–300 tokens/sec)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed Amazon Cloud API
- System Card & Safety Framework
- Amazon Production Safety & Alignment Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Amazon Nova Lite Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $14.15/mo vs $20 flat plan).
Break-even point: ~1,709 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Amazon Nova Lite:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 31.2%
- GPQA Diamond
- 42%
- MMLU-Pro
- 61.2%
- HumanEval
- 80.5%
- Humanity's Last Exam
- 4%
- Terminal-Bench
- 20.5%
- SciCode
- 21%
- LiveCodeBench
- 34.2%
- AIME
- 39.5%
- Long-Context Reasoning
- 66%
- Chatbot Arena Elo
- 1230pts
Strengths
- 300K のコンテキストウィンドウと最大 8K トークンの出力容量（SWE-bench Verified 31.2% · GPQA Diamond 42%）
- 毎秒 135 トークンの高速スループットと、初回トークン到達時間（TTFT）わずか 280ms の低遅延
- 優れたAPI経済性（1Mトークンあたり入力$0.06・出力$0.24）に加え、プロンプトキャッシュや構造化JSON出力・関数呼び出しに完全対応
Limitations & Trade-offs
- クラウド専用のプロプライエタリモデルのため、モデル重みをダウンロードしてオフライン実行することはできません
- 極めて高度な専門科学の証明問題では、上位の大型推論特化モデルの方がより深い洞察を提供する場合があります
Editorial Assessment
知能指数 38/100、300K コンテキスト、毎秒 135 トークンの速度を兼ね備えた Amazon Nova Lite は、Amazon のラインナップにおいて非常に実用性の高い主力モデルです。
Best for: テキストと画像のネイティブ・マルチモーダル理解および図表・ドキュメント解析、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。
Compare Amazon Nova Lite
Frequently Asked Questions about Amazon Nova Lite
How much does the Amazon Nova Lite API cost per 1M tokens?+
Amazon Nova Lite by Amazon is priced at $0.06 per 1M input tokens and $0.24 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.015 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Amazon Nova Lite pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Amazon Nova Lite's context window?+
Amazon Nova Lite features a 300K tokens context window, which equals approximately 225,000 English words or ~600 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.
Can I run Amazon Nova Lite locally on my own GPU (Open Weights)?+
No, Amazon Nova Lite is a proprietary closed-weights model hosted by Amazon. It cannot be downloaded for local GPU execution and must be accessed via Amazon's official API or cloud platform.
Does Amazon train on data sent to the Amazon Nova Lite API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Amazon Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Amazon Cloud API & Enterprise Endpoints.
How does Amazon Nova Lite perform on coding and reasoning benchmarks?+
Amazon Nova Lite achieves a composite Intelligence Index of 38/100, scoring 31.2% on SWE-bench Verified, 42% on GPQA Diamond, 61.2% on MMLU-Pro, and 1230 pts on Chatbot Arena Elo.
What is Amazon Nova Lite best used for?+
Amazon Nova Lite is best suited for: テキストと画像のネイティブ・マルチモーダル理解および図表・ドキュメント解析、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。. Assessment: 知能指数 38/100、300K コンテキスト、毎秒 135 トークンの速度を兼ね備えた Amazon Nova Lite は、Amazon のラインナップにおいて非常に実用性の高い主力モデルです。
Amazon Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Amazon's flagship reasoning tier:
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Amazon Nova Lite:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
An open standard created by Anthropic that allows AI applications and agents to connect seamlessly to local filesystems, development environments, and third-party APIs via standardized server interfaces.
A cost and latency optimization where inference providers store pre-computed attention states for repeated prompt prefixes. Reusing cached tokens typically slashes API input costs by 50% to 90% and cuts TTFT substantially.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.