Skip to content

Nova Micro

Nova Micro delivers text-only inference at high throughput with per-token pricing below multimodal Nova models in the same generation, purpose-built for latency-sensitive applications at scale.

index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'amazon/nova-micro',
prompt: 'Why is the sky blue?'
})

More models by Amazon

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
300K
0.3s
$0.06/M$0.24/M
bedrock logo
12/03/2024
300K
0.4s
$0.80/M$3.20/M
bedrock logo
12/03/2024
1M
0.3s
225tps
$0.30/M$2.50/M
Read:$0.07/M
Write:
bedrock logo
12/01/2024
$0.02/M
bedrock logo
04/01/2024