Nova Premier 1.0
VerifiedAmazon's multimodal model built for million-token text and image tasks.
About Nova Premier 1.0
Nova Premier 1.0 combines a transformer-based backbone with dedicated vision encoders. This design enables joint processing of lengthy documents and accompanying images without intermediate summarization. The one-million-token context window is achieved through efficient attention mechanisms and memory optimizations.
Its primary strengths include coherent reasoning across very long multimodal sequences and reliable handling of enterprise-scale inputs. Because the weights remain proprietary, Amazon maintains full control over updates, safety filters, and deployment infrastructure. The model therefore suits regulated industries that prioritize consistency and auditability.
Typical usage covers legal document review paired with charts, medical case analysis that merges reports and scans, and large-scale content summarization projects. Developers integrate it via Amazon's managed APIs to avoid infrastructure overhead while leveraging the full context capacity.
Capabilities
How Nova Premier 1.0 compares
Nova Premier 1.0 (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Nova Premier 1.0 ranks #70 of 97
Nova Premier 1.0Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Large-scale Legal Document Review
Processes million-token contracts and case files containing text, charts, and images to identify clauses, inconsistencies, and supporting visual evidence in one pass.
Scientific Paper Analysis
Handles multimodal research papers by reasoning across full text, embedded figures, and data tables to extract insights and cross-reference findings.
Enterprise Report Summarization
Comprehends extensive internal reports with diagrams and images, delivering structured summaries and answers to complex queries about operations or strategy.
Strengths & limitations
Strengths
- +Handles up to 1M token contexts
- +Native multimodal text and image support
- +Strong integration of visual and textual data
Limitations
- –Limited to text and image modalities
- –High context lengths may increase latency
- –No audio or video processing
Cost calculator
Estimate what Nova Premier 1.0 would cost for your usage.
Based on Nova Premier 1.0's $2.50/1M input · $12.50/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "amazon/nova-premier-v1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: amazon/nova-premier-v1
Editor's verdict
Nova Premier 1.0 is Amazon's proprietary multimodal with a 1000K-token context window.
At $12.50 per 1M output tokens, it is premium-priced for its class.
It is available through Amazon's API and aggregators like OpenRouter.
Best suited to handles up to 1m token contexts and native multimodal text and image support.
Frequently asked questions
The model supports up to 1,000,000 tokens, enabling analysis of very large documents and conversations.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Nova models
Sibling versions in the Nova family from Amazon.
Similar models
Other multimodal worth comparing.