Amazon · Model
Nova 2 Lite pricing, context window and specs
Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens, and reads up to 1,000,000 tokens per request. By blended price it is the cheapest of Amazon’s 2 current models here.
- Input / 1M
- $0.30
- Output / 1M
- $2.50
- Cached / 1M
- –
- Context
- 1,000,000
- Max output
- 65,535
- Released
- 2025-12-02
Estimate your cost with Nova 2 LiteCompare all Amazon modelsCount tokens for Nova 2 Lite
Pricing
Nova 2 Lite API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.30 | $2.50 |
Output costs 8.3× the input price, so long replies drive the bill more than long prompts. No cached-input price is published, so repeated prompt prefixes are billed at the full input price.
Examples
What Nova 2 Lite costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot | 1,500 / 400 | 1,000 | $0.00145 | $44.10 |
| RAG app | 6,000 / 500 | 500 | $0.00305 | $46.39 |
| Coding agent | 40,000 / 2,000 | 200 | $0.017 | $103.42 |
| Document summariser | 8,000 / 600 | 300 | $0.0039 | $35.59 |
Change any number in the cost calculator.
Context
Context window
Nova 2 Lite accepts up to 1,000,000 tokens per request, roughly 750,000 English words or 1,500 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 65,535 tokens.
Filling the whole window with one prompt costs about $0.30 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- No
- Structured output
- No
- Open weights
- No
- Accepts
- text, image, video, file
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Nova 2 Lite model ID
- OpenRouter
amazon/nova-2-lite-v1
Use the OpenRouter ID when calling it through OpenRouter; Amazon’s own API may name it differently. See the model ID reference for the providers we document.
Amazon
Where Nova 2 Lite sits in Amazon’s line-up
Ranked by blended price (three parts input to one part output, $0.85 per 1M for Nova 2 Lite), it is the cheapest of Amazon’s 2 current models here. One step up, Nova Premier 1.0 costs $5 (5.9× as much). Unlike Nova 2 Lite, it doesn’t accept files or video, caps a reply at 32,000 tokens (65,535 here) and has no reasoning mode. See every Amazon model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova 2 Lite (this page) | $0.30 | $2.50 | 1,000,000 | 2025-12-02 |
| Nova Premier 1.0 | $2.50 | $12.50 | 1,000,000 | 2025-10-31 |
Amazon’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of Nova 2 Lite
The previous model in this line is Nova Lite 1.0, first listed on 2024-12-05. Compared with it, Nova 2 Lite’s input price is 400% higher and its output price is 942% higher, and the context window went from 300,000 to 1,000,000 tokens.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova Lite 1.0 | $0.06 | $0.24 | 300,000 | 2024-12-05 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- Qwen3.5-9BQwen87% cheaper
- Seed 1.6 FlashByteDance Seed85% cheaper
- GPT-6 LunaOpenAI76% cheaper
- Claude Haiku 5.5Anthropic76% cheaper
- GLM 4.6VZ.ai47% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Gemini 3.5 Flash LiteGoogle$0.30 / $2.50
- Seed 2.1 TurboByteDance Seed$0.50 / $2.50
- Qwen3.5-122B-A10BQwen$0.26 / $2.08
- Mistral Large 4Mistral$0.68 / $2.09
- Nemotron 3 UltraNVIDIA$0.60 / $2.40
Current models from other major providers, closest blended price.
FAQ
Nova 2 Lite questions
How much does Nova 2 Lite cost?
Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00145. Use the LLM cost calculator for your own workload.
What is Nova 2 Lite’s context window?
1,000,000 tokens, about 750,000 English words or 1,500 printed pages, shared between your prompt and the reply. A single reply can be up to 65,535 tokens.
Does Nova 2 Lite support prompt caching and batch requests?
No cached-input price is published for it. No batch price is published for it.
What are cheaper alternatives to Nova 2 Lite?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.5-9B (87% cheaper), Seed 1.6 Flash (85% cheaper), GPT-6 Luna (76% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Nova 2 Lite?
On OpenRouter it is amazon/nova-2-lite-v1. Amazon’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
What did Nova 2 Lite replace?
The previous Amazon model in the same line is Nova Lite 1.0, first listed on 2024-12-05. Compared with it, Nova 2 Lite’s input price is 400% higher and its output price is 942% higher. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is Nova 2 Lite open source?
No, Nova 2 Lite is only available through Amazon’s API and partners; its weights aren’t published.