AmazonReleased on Nov 20, 2024

Nova Lite: API Pricing, Context Window & Benchmarks

Nova Lite is a language model from Amazon, released in November 2024, with multimodal input.

A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.

Input
TextImage
Output
Text
Speed
Latency p95500ms
Throughput P95100char/s
Cost
$0.08/ 1M · 8:1 in:out
$0.06 in · $0.24 out

Nova Lite benchmarks

Rankings

Quality Tracker

Nova Lite Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Sat Jul 25 2026
Notice missing or incorrect data?

Nova Lite pricing

Providers

Nova Lite starts at $0.0600 per million input tokens and $0.240 per million output tokens via Bedrock.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Bedrock logoBedrock
$0.0600$0.240300.0K/2.0K
—/0.50
100/—
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Nova Lite context window

Input and output token limits for Nova Lite, plus how it ranks on long-context understanding.

InputOutput
300Ktokens
2Ktokens
≈ 451 pages of text
300K
8K128K1M

Nova Lite API

Available from the model provider

Nova Lite has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Nova Lite latency

Nova Lite time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Nova Lite examples

Recent arena outputs from Nova Lite, picked from the highest-ranked matchups.

Nova Lite license

Nova Lite is a proprietary model available under its provider's product and API terms.

License
Proprietary
Hosted access

Proprietary license - usage restrictions apply

Nova Lite resources

Official sources for Nova Lite: api documentation, paper or system card.

Nova Lite vs other models

The most-compared alternatives to Nova Lite are Claude 3 Opus, Llama 3.1 405B Instruct, GPT-4 Turbo. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Nova Lite

Models ranked just above and below Nova Lite by LLM Stats score.

 

Claude 3 Opus

Score pending
DetailsCompare
 

Llama 3.1 405B Instruct

Score pending
DetailsCompare
 

GPT-4 Turbo

Score pending
DetailsCompare
 

Llama 3.1 70B Instruct

Score pending
DetailsCompare
 

Grok-2 mini

Score pending
DetailsCompare
 

Mistral Small 3.2 24B Instruct

Score pending
DetailsCompare

FAQ

Common questions about Nova Lite.

When was Nova Lite released?

Nova Lite was released on November 20, 2024 by Amazon. This is the official Nova Lite release date tracked on LLM Stats.

How much does Nova Lite cost?

Nova Lite pricing starts at $0.06 per million input tokens and $0.24 per million output tokens via Bedrock, the lowest price among tracked providers.

Is Nova Lite available via API?

Yes, Nova Lite is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

Who created Nova Lite?

Nova Lite was created by Amazon.

What is the license for Nova Lite?

Nova Lite is released under the Proprietary license.

Is Nova Lite multimodal?

Yes, Nova Lite is multimodal and can accept both text and images as input.

What is Nova Lite latency?

Nova Lite p95 time to first token is 0.50 seconds via Bedrock over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Nova Lite?

Nova Lite is available through 1 provider including Bedrock.

Where is the Nova Lite paper or technical report?

Nova Lite has a paper or technical report available at https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card. Use that source for architecture, training, release and evaluation details.

What models should I compare Nova Lite against?

Common Nova Lite comparisons include Nova Lite vs Claude 3 Opus, Nova Lite vs Llama 3.1 405B Instruct, Nova Lite vs GPT-4 Turbo. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.