Context
300K
Max output
10K
Serving providers
3
Cheapest input
$0.06 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
129 t/s
tokens / second
Time to first token
7.50s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 0% | default | — | |
| GPQA Diamond | 43% | default | — | |
| Humanity's Last Exam | 5% | default | — | |
| IFBench | 34% | default | — | |
| LiveCodeBench | 17% | default | — | |
| Long-Context Reasoning | 18% | default | — | |
| MMLU-Pro | 59% | default | — | |
| MMMU-Pro | 38% | default | — | |
| Omniscience | -40.4 | default | — | |
| SciCode | 14% | default | — | |
| TerminalBench Hard | 1% | default | — | |
| τ²-bench | 18% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Amazon BedrockCheapest | $0.06 | $0.24 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Amazon NovaCheapest | $0.06 | $0.24 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Vercel AI GatewayCheapest | $0.06 | $0.24 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$31
estimated / month
Model IDs
copy the exact identifier for your platformamazon.nova-lite-v1:0amazon-nova/nova-lite-v1vercel_ai_gateway/amazon/nova-lite
Frequently asked questions
Nova Lite 1.0 pricing, context and availabilityHow much does Nova Lite 1.0 cost?
Nova Lite 1.0 costs $0.06 per 1M input tokens and $0.24 per 1M output tokens at its cheapest provider via Amazon Bedrock.
What is the context window of Nova Lite 1.0?
Nova Lite 1.0 accepts up to 300K tokens of context and can return up to 10K output tokens.
Which providers serve Nova Lite 1.0?
Nova Lite 1.0 is available from 3 serving providers, each with its own pricing and model ID. Amazon Bedrock is currently the cheapest.
What can Nova Lite 1.0 do?
Nova Lite 1.0 supports image input (vision), tool use, prompt caching and structured output.
Other Amazon models
compare pricing across the Amazon lineup Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI