Amazon Nova Micro 1.0
Neural Network
Amazon Nova Micro is Amazon's lowest-latency text model. Use the Nova Micro API for fast scenarios.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 128 000 tokens
- Max answer length
- 5 120 tokens
- Capabilities
- function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Amazon Nova Micro 1.0?
Amazon Nova Micro 1.0 is a text-only model from Amazon's Nova lineup, offering the lowest latency in the family while remaining one of the most cost-effective. It is ideal for tasks where response speed and high volume are more important than complex, multi-step reasoning. In BotHub, the model is accessible from Russia without a VPN or foreign card, with pay-as-you-go billing via Russian cards and no subscription required. Access over 250 other models in one window: compare responses and switch to a more powerful model without rewriting your integration using our unified OpenAI-compatible API, AES-GCM encryption, and enterprise features like contracts, invoices, EDI, and an admin panel with limits. The Nova Micro API is perfect for building first-line support chatbots requiring instant responses, classifying and routing inquiries, tagging large text streams, summarizing emails and tickets, and serving as a fast pre-processing layer before more expensive models.Frequently asked questions about Amazon Nova Micro 1.0
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.
This is an Amazon text model from the Nova lineup for everyday tasks: answering questions, rewriting and summarizing text, parsing uploaded documents, data extraction, and code suggestions. It accepts text, documents, and images as input, and the 128,000-token context window allows you to work with long materials in their entirety.
The model generates up to 5,120 tokens per response, which is roughly several pages of text. If you need extensive material, break the work into parts: ask for an outline, then section by section. The 128,000-token context maintains the entire conversation, so coherence between parts is not lost.
A dedicated step-by-step reasoning mode is not specified in our data, so we cannot promise it. In practice, a simple trick helps: ask the model to write out the solution step-by-step in the response — this way it breaks down the problem sequentially, and you can see the logic and verify each step.
Yes, function calling and structured JSON output are supported. Describe your tool schema, and the model will return arguments in the required format, which is easy to pass to your code. Through the unified OpenAI-compatible BotHub API, this connects as usual, and you can switch to another model if needed without rewriting your integration.
Images and documents — yes: you can send a screenshot, photo of a page, PDF, or table and ask to analyze the content, summarize it, or extract specific fields. Audio and video are not in the list of supported inputs for this model; for those, use specialized models from the same window in BotHub.
We do not have data on the quality of its Russian language performance, so we will not provide an assessment — it is easier to test it with your own task. Run a couple of typical queries and compare the result with other models in the same BotHub window: access from Russia without a VPN or foreign card, payment in rubles.