Amazon: Nova Pro

Flagship model for demanding analysis, coding, and production agent workflows

Model lab: Amazon
Model family: nova-pro

Modalitiestext, image, video, pdf → text

Context window300,000

Maximum output10,000

InputUSD 0.64 / 1M tokens

OutputUSD 2.56 / 1M tokens

Try now

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-pro.

import os
import requests

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

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 Pro API Pricing

Type	Price information
Input	USD 0.64 / 1M tokens
Output	USD 2.56 / 1M tokens
Cached input	USD 0.16 / 1M tokens
Cache write	USD 0.64 / 1M tokens

Benchmarks

Intelligence Index · v4.37

Coding Index—

Agentic Index—

Performance

Output speed129.42 tokens/s

Time to first token1.1 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput129.42 tok/sCurrent

Time to first token1.1 sCurrent

End-to-end latency8.1 sCurrent

Throughput

Current129.42 tok/s

Window average125.3 tok/s

Time to first token

Current1.1 s

Window average1.2 s

End-to-end latency

Current8.1 s

Window average7.5 s

Tail latency (P99)

Current16.2 s

Window average17.4 s

Prompt cache hit rate

Current26.1%

Window average23.3%

Error rate

Current0.0%

Window average0.2%

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 Pro Compare models

Model	Input price	Output price	Context window	Capabilities
Nova ProThis page	USD 0.64 / 1M tokens	USD 2.56 / 1M tokens	300,000	Text output · Tool calling
Nova Pro 1.0	USD 0.7344 / 1M tokens	USD 2.9368 / 1M tokens	300,000	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

Model specifications

Input: text, image, video, pdf
Output: text
Context window: 300,000
Maximum output: 10,000
Release date: 2024-12-03
Attachments: Yes
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Nova Pro for?

Flagship model for demanding analysis, coding, and production agent workflows

What inputs and outputs does Nova Pro support?

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

How is Nova Pro priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.64 / 1M tokens; Output USD 2.56 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Nova Pro?

Current model records list Context window 300,000 tokens; Maximum output 10,000 tokens.

What model parameter does the Quickstart use?

The example uses amazon/nova-pro. 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.