Amazon Nova Premier V1
Neural Network
Amazon Nova Premier V1 is Amazon's multimodal model for complex reasoning, available in BotHub via the nova premier api.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Amazon Nova Premier V1?
Amazon Nova Premier V1 is the flagship model in Amazon's Nova multimodal lineup, designed for tasks requiring complex reasoning chains: parsing conditions, analyzing data from text and images, and step-by-step output generation. Its second role is acting as a teacher for distillation, where the quality of a large model is transferred to compact solutions for specific tasks. In BotHub, the model works without a VPN or foreign card: you pay with a Russian card in rubles and consume tokens as you go, with no subscription. Other neural networks—over 250 models—are available in the same window, making it easy to compare answers for a single request. Developers have access to a unified OpenAI-compatible API, while companies get contracts, invoices, electronic document management, and an admin panel with limits. For analysts, Nova Premier helps parse reports and data; for engineers, it helps design service logic and debug; for researchers, it helps prepare distilled model versions for their tasks; and for product teams, it helps prototype scenarios involving both text and image inputs.Frequently asked questions about Amazon Nova Premier V1
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.
The model works with a context of up to a million tokens, so it can handle long documents, reports, and large codebases. It accepts not only text but also images and documents, can call functions, and output structured JSON. Suitable for analytics, documentation parsing, refactoring, and debugging.
In a single response, the model outputs up to 32,000 tokens—that's several dozen pages of text. The total context holds up to a million tokens, so you can upload a voluminous document and ask for a summary, analysis, or rewritten version without losing details.
There is no specific indication of a reasoning mode in our data, so we won't promise it—it is not a confirmed fact. However, the model is designed for tasks requiring sequential analysis: data analysis, working with code, parsing large documents, and preparing structured responses.
Yes, function calling and structured JSON output are supported—this is confirmed by the model's data. This means it can be integrated into your own service: the response will return in the required schema, and the unified BotHub API allows you to switch to another model if needed without rewriting the integration.
It accepts not only text but also images and documents as input: you can upload a scan, PDF page, or table and ask questions about the content. Audio and video are not marked as supported formats in our data, so for such files, you should first check availability in the chat.
We have no data on its Russian language proficiency, so we won't praise or criticize the model. It is more practical to test it with your own material: upload a text fragment or document and evaluate the result—tests in BotHub are without subscription, pay-as-you-go for tokens.