Skip to content

Model vendor

Amazon models: API pricing and providers

4 Amazon models with Amazon's published list rates and the providers that serve each one. You call them through INFRO on a provider account you connect; that account bills you, and INFRO adds 0% to model spend.

Rates checked 2026-10-05.

Amazon models

ModelModalityList rateProviders
Amazon Nova 2 Lite
amazon/nova-2-lite
Fast low-cost multimodal reasoning
Text$0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.075 per 1M tokens1
Amazon Nova Pro
amazon/nova-pro
Balanced multimodal (text, image, video input)
Text$0.80 per 1M input tokens and $3.20 per 1M output tokens, with cached input at $0.20 per 1M tokens1
Amazon Nova Lite
amazon/nova-lite
Low-cost multimodal (text, image, video input)
Text$0.06 per 1M input tokens and $0.24 per 1M output tokens, with cached input at $0.015 per 1M tokens1
Amazon Nova Micro
amazon/nova-micro
Text-only, lowest latency and cost
Text$0.035 per 1M input tokens and $0.14 per 1M output tokens, with cached input at $0.0088 per 1M tokens1

Amazon models: questions

Which Amazon models does this reference list?
4 Amazon models: 4 text. Each has its own page with Amazon's list rate and the providers that serve it.
Which providers serve Amazon models?
OpenRouter. You connect your own account with any of them; INFRO routes between the ones you connect.
What is the lowest Amazon input rate listed?
Amazon Nova Micro, at $0.035 per 1M input tokens and $0.14 per 1M output tokens, with cached input at $0.0088 per 1M tokens on Amazon's list (checked 2026-10-05).
Does INFRO add a markup to Amazon model usage?
No. Your Amazon or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Other model vendors

Search and filter every model