Nova 2 Lite
Neural Network
Nova 2 Lite is Amazon's fast multimodal model for daily tasks: the Nova 2 Lite API accepts text, images, and video.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 1 000 000 tokens
- Max answer length
- 65 535 tokens
- Reasoning effort
- low, medium, high
- Capabilities
- reasoning, function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Nova 2 Lite?
Nova 2 Lite is an Amazon Nova family model for daily workflows: it reasons through prompts while remaining fast and token-efficient. It accepts text, images, and video, and outputs text, making it suitable for analyzing documents with screenshots or summarizing clips. In BotHub, it is available without VPN or foreign cards: pay with Russian cards in rubles only for tokens used, which do not expire. Access over 250 models in one place, and use the unified BotHub API to switch models without rewriting code. Traffic is encrypted via AES-GCM, chats are not saved, and companies get contracts, invoices, EDI, and an admin panel with limits. Nova 2 Lite is commonly used for mass support ticket processing, data extraction from scans and photos, draft annotations, meeting video analysis, and automating routine chains where speed and cost per call are critical.Frequently asked questions about Nova 2 Lite
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
Amazon's Nova 2 Lite is a text model with a reasoning mode that accepts images and documents. It is suitable for coding, analyzing long materials, extracting data from files and screenshots, and agent scenarios with function calling. Context is up to one million tokens.
The model outputs up to 65,535 tokens per response—enough for a lengthy article, documentation, or a large code module. If the material is longer, ask it to continue: the one-million-token context allows it to keep the entire conversation and previously written parts in view.
Yes, reasoning mode is supported: the model breaks down the task step-by-step before formulating a conclusion. This helps with math, logic, code debugging, and multi-step instructions. For simple tasks, a standard request is sufficient; for complex ones, ask it to explain the solution process in detail.
Yes, both. The model calls your functions and returns structured JSON according to a specified schema, making it easy to integrate into agents, chatbots, and data processing pipelines. In BotHub, this works via a unified OpenAI-compatible API—you can switch models without rewriting your integration.
Images and documents—yes: you can send a screenshot, diagram, table, or PDF and ask it to analyze the content. Audio and video input are not supported in our data, so for voiceovers or video file analysis, please choose a specialized model from the catalog. The model responds with text.
We have no data on language capabilities, so we cannot promise anything specific—test it with your task, it's quick. However, access to the model in BotHub is definitely without VPN or foreign cards: pay with Russian cards, based on actual token usage.