Primary use stated or inferred cautiously from official documentation.
AWS
AMAZON / amazon.nova-2-lite-v1:0
Amazon Nova 2 Lite
Long documents, video, and enterprise tasks on AWS.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | amazon.nova-2-lite-v1:0 |
|---|---|
| Model type | Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | DEC 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Video · Document |
| Exit | Text |
| Context window | 1,000,000 tokens |
| maximum output | 65.536 tokens |
| Reasoning | Configurable effort |
| Published tools | Code interpreter · Web grounding · Remote MCP |
| Structured Outings | Supported |
| Batch processing | Available on Amazon Bedrock |
| Prompt cache | Supported |
| Fine-tuning | Supported |
| Verified platforms | Amazon Bedrock |
Long documents, video, and enterprise tasks on AWS.
Pricing depends on the Amazon Bedrock region and inference mode.
03 / CAPABILITIES
What it can do
Orientation
Long documents, video, and enterprise tasks on AWS.
Context
1.000.000 tokens · 65.536 tokens
Tools and integration
Code interpreter · Web grounding · Remote MCP
Access
Amazon Bedrock
Input modalities
TextImageVideoDocument
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source before budgeting for a deployment.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Aegis | 85,84 % | F1 | View source ↗ |
| WildGuard | 84,73 % | F1 | View source ↗ |
| Jigsaw | 56,53 % | F1 | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Amazon Nova 2 Lite
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
Private Documents with AI: How to Decide What Can Leave the Perimeter and What Requires Review
An operational route for deciding whether a search, summarization, extraction, classification, or drafting workflow can process private documents directly, in minimized form, in segments, or within a controlled environment. The focus is not on selecting a technology by default, but on defining data, transformations, controls, and human review before production.
22 Sep 2026 ↗
Amazon Nova 2 Lite vs. Claude Fable 5.1 for Document Data Extraction: How to Design a Reproducible Comparison
The available documentation describes the capabilities, pricing, and access policies of Amazon Nova 2 Lite and Claude Fable 5.1, but it does not provide an independent test using a shared corpus. This guide defines a protocol for comparing them in structured document extraction and explains which decisions can be made, which asymmetries must be disclosed, and when neither model should automate the workflow without human review.
22 Sep 2026 ↗
Amazon Nova 2 Lite: what to review when migrating from Nova 1 as context reaches one million tokens
Amazon Nova 2 Lite expands the technical contract available in Amazon Bedrock with a context window of up to one million tokens, a declared maximum output of 64,000 tokens, and configurable extended thinking. Those capabilities do not make a migration from Nova 1 an identifier-only change: they require renewed validation of APIs, limits, tools, timeouts, inference routes, and data controls.
22 Sep 2026 ↗
AEGIS: what this benchmark measures in manipulated academic images, and why detection, explanation, and localization are not the same result
AEGIS evaluates forensic analysis of AI-generated or AI-manipulated academic images through distinct tasks: deciding whether an alteration exists, explaining the clues, and identifying the affected region. This guide separates the claims each result can support from those that would require additional evidence before a system is used in scientific-integrity or editorial review.
19 Sep 2026 ↗
Amazon Nova 2 Lite: How to Calculate the Real Cost per Workflow Across Tokens, Cache, Service Tiers, and Failures
A guide to turning Amazon Bedrock unit pricing and telemetry into an auditable estimate of the cost per completed task with Amazon Nova 2 Lite. The method separates consumption, retries, cache, service tier, and validated outcome without assuming rates that are not provided by the available sources.
19 Sep 2026 ↗07 / SOURCES