Atlas / Models / Amazon / Amazon: Nova Pro 1.0

Amazon: Nova Pro 1.0✓ Catalog verified

amazon/nova-pro-v1

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

Input price
$0.80 /1M
Output price
$3.20 /1M
Context
300K
Modalities
textimage
Released
Dec 5, 2024
Tool calling
✓ Yes
Atlas signal
82/100
01

Overview

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

Access: available through the official Amazon API. Context window: 300K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Sep 19, 2026
02

Specifications

API identifieramazon/nova-pro-v1
ProviderAmazon
Model typeMultimodal LLM
Context window300K catalog
Input modalitiestext · image
Output modalitiestext
ReleasedDec 5, 2024
TokenizerNova
ModeratedYes
Architecture modalitytext+image->text
Supported parameters
max_tokensstoptemperaturetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for amazon/nova-pro-v1 as published in the catalog.

$0.80
Input /1M
$3.20
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$8e-7$0.80 / 1MPer input token
Completion tokens$0.0000032$3.20 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$1.04Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Amazon: Nova Pro 1.0
MMLU Signal (Reasoning)
79signal
Coding Signal (HumanEval proxy)
85signal
Math Signal (GSM8K proxy)
79signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Amazon: Nova Pro 1.0 through an OpenAI-compatible client.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="amazon/nova-pro-v1",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Amazon: Nova Pro 1.0 cost?

$0.80 per 1M input tokens and $3.20 per 1M output tokens on the official Amazon API.

What is the context window of Amazon: Nova Pro 1.0?

Amazon: Nova Pro 1.0 supports up to 300K tokens of context.

Does Amazon: Nova Pro 1.0 support tool / function calling?

Yes, Amazon: Nova Pro 1.0 supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Amazon: Nova Pro 1.0?

Use the official Amazon API with the model id `amazon/nova-pro-v1`. See the Quick start section above for code examples.