Nova Premier 1.0

Amazon chattool_usevision Long

API ID: amazon/nova-premier-v1

Input Price
$2.50
/1M tokens
Output Price
$12.50
/1M tokens
Cached Input
$0.63
Save 75%

About Nova Premier 1.0

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

💰
Price Ranking
#1158 lowest price among 1240 Chat models

Model Specifications

Context Length
1.0M
Max Output
32k
Release Date
2025-10-31
Capabilities
chat tool_use vision
Input Modalities
textimage
Output Modalities
text

Best For

  • Image analysis, document understanding, visual Q&A
  • Conversations, content writing, general assistance

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$4.88
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$150.00
/month
1000 tickets/day, ~800 tokens each

Amazon Model Lineup

Compare all models from Amazon to find the best fit

Model Input Output Context Capabilities
Nova Premier 1.0 Current $2.50 $12.50 1.0M chat tool_use vision
Nova Micro 1.0 $0.04 $0.14 128k chat tool_use
Nova Lite 1.0 $0.06 $0.24 300k chat tool_use vision
Nova 2 Lite $0.30 $2.50 1.0M chat reasoning tool_use
Nova Pro 1.0 $0.80 $3.20 300k chat tool_use vision

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Anthropic Claude Opus 5 (batch)
Input: $2.50
Output: $12.50
Context: 1.0M
Anthropic Claude Opus 4.8 (batch)
Input: $2.50
Output: $12.50
Context: 1.0M
Anthropic Claude Opus 4.7 (batch)
Input: $2.50
Output: $12.50
Context: 1.0M
Anthropic Claude Opus 4.6 (batch)
Input: $2.50
Output: $12.50
Context: 1.0M

🚀 Quick Start

Get started with Nova Premier 1.0 API

OpenAI-compatible SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="amazon/nova-premier-v1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)