Amazon: Nova Premier

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

Model lab: Amazon
Model family: nova

Modalitiestext, image, video, pdf → text

Context window1,000,000

Maximum output10,000

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to amazon/nova-premier.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "amazon/nova-premier"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Nova Premier API Pricing

Price under review

Benchmarks

Intelligence Index · v4.39.2

Coding Index—

Agentic Index—

Performance

Performance trends

Throughput91.9 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.0 sCurrent

Throughput

Current91.9 tok/s

Window average90.2 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.0 s

Window average7.5 s

Tail latency (P99)

Current17.5 s

Window average17.0 s

Prompt cache hit rate

Current18.1%

Window average24.7%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Nova Premier Compare models

Model	Input price	Output price	Context window	Capabilities
Nova PremierThis page	Price under review	Price under review	1,000,000	Text output · Tool calling
Nova 2 Lite	USD 0.24 / 1M tokens · Maximum output 65535 tokens	USD 2 / 1M tokens · Maximum output 65535 tokens	1,000,000	Text output · Reasoning · Tool calling
Nova 2 Lite	USD 0.24 / 1M tokens	USD 2 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Nova Lite	USD 0.048 / 1M tokens	USD 0.192 / 1M tokens	300,000	Text output · Tool calling
Nova Pro	USD 0.64 / 1M tokens	USD 2.56 / 1M tokens	300,000	Text output · Tool calling

Model specifications

Input: text, image, video, pdf
Output: text
Context window: 1,000,000
Maximum output: 10,000
Release date: 2025-04-30
Attachments: Yes
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Nova Premier for?

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

What inputs and outputs does Nova Premier support?

Recorded inputs: text, images, video, PDF; outputs: text.

How is Nova Premier priced?

This page does not list a price for this model yet.

What specifications are recorded for Nova Premier?

Current model records list Context window 1,000,000 tokens; Maximum output 10,000 tokens.

What model parameter does the Quickstart use?

The example uses amazon/nova-premier. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.