1 Resposta
- Mais recentes
- Mais votos
- Mais comentários
1
If you're solely using On-Demand inferencing, you'll only be charged for the tokens that you pass in and receive back from Bedrock as specified in the pricing page. However, If you decide to go the Provisioned Throughput route, you'll be charged for Model Units (includes a limited about of tokens) 24/7 for either a 1 month or 6 month terms.
respondido há 3 meses
Conteúdo relevante
- AWS OFICIALAtualizada há 2 anos
the "pricing page" link is wrong (goes to Credly)
Page here: https://aws.amazon.com/bedrock/pricing/