impulse

Nova Lite

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output.

API id nova-lite-v1Released 5 Dec 2024 (Dec 2024)
Input / 1M
$0.06
at Amazon Nova
Output / 1M
$0.24
at Amazon Nova
Context window
300K
tokens
Max output
10K
tokens per reply
Hosts
3
7 listings
Released
Dec 2024
5 Dec 2024

Pricing

List prices at Amazon Nova, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.06$0.24

What it costs a month

At Amazon Nova list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$36.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$37.44
  • Coding agent1,000 requests a day, 40K in / 2K out$86.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$202
Use your own numbers

Where to run it

3 hosts serve Nova Lite. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
nova-lite-v1
$0.06 / $0.24
amazon.nova-lite-v1:0
$0.06 / $0.24
nova-lite
$0.06 / $0.24
Show 4 more listings: regions, snapshots and variants
Amazon Bedrock
us
us.amazon.nova-lite-v1:0
$0.06 / $0.24
apac
apac.amazon.nova-lite-v1:0
$0.063 / $0.252
+5% vs headline
us-gov-west-1
amazon.nova-lite-v1:0
$0.072 / $0.288
+20% vs headline
eu
eu.amazon.nova-lite-v1:0
$0.078 / $0.312
+30% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesPDFs
Produces
Text
Features
PDF inputPrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Amazon Nova.

Smaller Amazon models

  • Nova Micro
    Amazon · on Amazon Nova
    $0.035 / $0.14
    Lacks vision
    42% less

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    5% less
  • Qwen3.5 9B
    Alibaba Qwen · on EmpirioLabs AI
    $0.09 / $0.13
    Has every key capability
    5% less
  • GLM 5.3 Flash
    Zhipu AI · on CLF AI Gateway
    $0.06 / $0.20
    Has every key capability
    10% less
  • DeepSeek V4.1 Flash Fast
    DeepSeek · on Refuseless
    $0.05 / $0.15
    Has every key capability
    29% less

Call it

Using Amazon Nova's API.

Python
from litellm import completion

response = completion(
    model="amazon_nova/nova-lite-v1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nova Lite cost?

On Amazon Nova, Nova Lite costs $0.06 per million input tokens and $0.24 per million output tokens.

Which APIs offer Nova Lite?

Nova Lite runs on 3 APIs: Amazon Nova, Amazon Bedrock and Vercel AI Gateway.

What is Nova Lite's context window?

300K tokens, with up to 10K tokens in one reply.

Is Nova Lite being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Nova Lite?

Models that cost less and keep most of what it can do: Nova Micro on Amazon Nova (42% less) and MiniMax M3.1 Flash on Refuseless (5% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Nova Lite released?

Amazon released it on 5 Dec 2024.

What is Nova Lite's API model id?

Use nova-lite-v1 with Amazon Nova. Other hosts use their own ids: amazon.nova-lite-v1:0 on Amazon Bedrock, nova-lite on Vercel AI Gateway.

Sources

Raw catalog entry for nova-lite-v1 on Amazon Nova
{
  "input_cost_per_token": 6e-8,
  "litellm_provider": "amazon_nova",
  "max_input_tokens": 300000,
  "max_output_tokens": 10000,
  "mode": "chat",
  "output_cost_per_token": 2.4e-7,
  "supports_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_response_schema": true,
  "supports_vision": true
}